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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    125
    -0.07
    她的
    -0.07
     Spike
    -0.07
     Buildings
    -0.06
    {}'.
    -0.06
     후
    -0.06
    _gr
    -0.06
     Fay
    -0.06
     perks
    -0.06
     Hao
    -0.06
    POSITIVE LOGITS
     usu
    0.07
    Affected
    0.06
    _charset
    0.06
    _neg
    0.06
    าชน
    0.06
    nement
    0.06
    development
    0.06
    lags
    0.06
    (bodyParser
    0.06
    tf
    0.06
    Act Density 0.002%

    No Known Activations