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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron activates on square-bracket tokens that denote indexing operations (e.g. array or list accesses).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Hell
    -0.08
    zeigt
    -0.07
    زارش
    -0.07
     Specs
    -0.06
    ulses
    -0.06
    Ps
    -0.06
    ática
    -0.06
    Glass
    -0.06
    inery
    -0.06
    Wrapped
    -0.06
    POSITIVE LOGITS
     společně
    0.07
    /null
    0.07
    �
    0.07
    HTTPHeader
    0.07
    jící
    0.07
     režim
    0.06
     lobbyists
    0.06
     entertain
    0.06
     baktı
    0.06
    foy
    0.06
    Act Density 0.052%

    No Known Activations