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

    Neuronpedia

    INDEX
    Explanations

    Actions and processes

    np_max-act · gemini-2.0-flash

    This neuron activates on instructional action verbs (like "create," "represent," "provide") used in explanatory or definitional contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    alties
    -0.08
    ुपए
    -0.08
     nového
    -0.07
    愿
    -0.07
    _merged
    -0.07
    νει
    -0.07
     인간
    -0.07
    Nonce
    -0.07
    ycin
    -0.07
    gon
    -0.06
    POSITIVE LOGITS
     Contractor
    0.06
     hareket
    0.06
     underscores
    0.06
    ikki
    0.06
    down
    0.06
    (..
    0.06
    eric
    0.06
     Battle
    0.05
     populate
    0.05
     Chat
    0.05
    Act Density 0.108%

    No Known Activations