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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron consistently activates on the preposition “of,” especially in formal or list-like phrases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Luke
    -0.06
     Ford
    -0.06
     Sites
    -0.06
    .getDeclared
    -0.06
    ्यवस
    -0.06
     eleven
    -0.06
     sortBy
    -0.06
     Lâm
    -0.06
     например
    -0.06
    ност
    -0.06
    POSITIVE LOGITS
    Bindable
    0.08
    due
    0.07
     italiana
    0.06
    _SM
    0.06
    SEP
    0.06
     apparel
    0.06
    _interrupt
    0.06
     novamente
    0.06
     peer
    0.06
    __);↵
    0.06
    Act Density 0.033%

    No Known Activations