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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invested
    -0.07
    shares
    -0.07
     installing
    -0.07
     Tropical
    -0.07
    车祸
    -0.07
    况且
    -0.07
     ila
    -0.07
     Traditional
    -0.06
     FetchType
    -0.06
     windy
    -0.06
    POSITIVE LOGITS
    _res
    0.08
    $.
    0.07
    IA
    0.07
    𝑭
    0.07
    дут
    0.07
    RESP
    0.07
     tslib
    0.07
    ORIA
    0.06
    שיר
    0.06
    SG
    0.06
    Act Density 0.000%

    No Known Activations