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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash

    This neuron doesn’t respond to any input—it remains inactive for all tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    佐
    -0.08
    _from
    -0.07
     PRI
    -0.07
     Outs
    -0.07
     freeway
    -0.06
    ころ
    -0.06
    λεύ
    -0.06
     بشر
    -0.06
     правиль
    -0.06
    iterated
    -0.06
    POSITIVE LOGITS
    ños
    0.06
     bourgeoisie
    0.06
     picking
    0.06
     다양한
    0.06
     IKE
    0.06
     şans
    0.06
    .gson
    0.06
    ’s
    0.06
    -spe
    0.06
    etSocketAddress
    0.06
    Act Density 0.117%

    No Known Activations