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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    This neuron is effectively silent—it never activates on any input.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bulunur
    -0.06
            ↵        ↵        ↵
    -0.06
    abetic
    -0.06
    anı
    -0.06
     rychle
    -0.06
     fair
    -0.06
    anca
    -0.06
     Sullivan
    -0.06
    _AF
    -0.06
     Barrett
    -0.06
    POSITIVE LOGITS
    trecht
    0.08
    _DDR
    0.06
     викон
    0.06
     Negot
    0.06
     Franti
    0.06
     UBND
    0.06
    <Scalar
    0.06
    선을
    0.06
    hip
    0.06
    isque
    0.06
    Act Density 0.002%

    No Known Activations