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

    Neuronpedia

    INDEX
    Explanations

    shared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ация
    -0.07
    рою
    -0.07
     Frozen
    -0.06
     experts
    -0.06
    ipated
    -0.06
    emente
    -0.06
    角
    -0.06
    šel
    -0.06
    арам
    -0.06
     betrayed
    -0.06
    POSITIVE LOGITS
    _InitStructure
    0.07
    [url
    0.06
    _rnn
    0.06
    盤
    0.06
    .StylePriority
    0.06
    .tf
    0.06
    芯
    0.06
    _pel
    0.06
     Treat
    0.06
    (OS
    0.06
    Act Density 0.025%

    No Known Activations