Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Time progression

    np_max-act · gemini-2.0-flash

    methods and processes related to manufacturing and shaping materials, particularly in the context of pharmaceuticals and resin.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects sequence-transition adverbs (e.g. "Then," "Subsequently," "Thereafter") that mark the next step in a procedure.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     infield
    -0.06
    siblings
    -0.06
     magna
    -0.06
    dob
    -0.06
    したら
    -0.06
     Ronaldo
    -0.06
     Kelley
    -0.05
    emás
    -0.05
     �
    -0.05
    .Show
    -0.05
    POSITIVE LOGITS
     breaks
    0.07
     Auth
    0.07
     green
    0.07
     portrays
    0.06
    #\
    0.06
     set
    0.06
     Rubber
    0.06
     Applying
    0.06
     Sail
    0.06
    essor
    0.06
    Act Density 0.052%

    No Known Activations