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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash

    The neuron activates on inclusive “we all” constructions—i.e. instances of the phrase “we all.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rehab
    -0.07
     appare
    -0.07
     converse
    -0.06
    IntoConstraints
    -0.06
     gsi
    -0.06
     storytelling
    -0.06
     dress
    -0.06
     turf
    -0.06
    Orig
    -0.06
     mixin
    -0.06
    POSITIVE LOGITS
     meslek
    0.07
    	elem
    0.06
    /T
    0.06
     incap
    0.06
     kel
    0.06
    (Locale
    0.06
     '.',
    0.06
    ausal
    0.06
    나요
    0.06
     สม
    0.06
    Act Density 0.012%

    No Known Activations