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

    Neuronpedia

    INDEX
    Explanations

    reading data files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DataFrame
    0.80
     dataframe
    0.71
     Data
    0.71
     Datas
    0.70
     datas
    0.68
     dat
    0.68
    DataFrame
    0.64
    Data
    0.64
     Dat
    0.63
    datas
    0.62
    POSITIVE LOGITS
    ambi
    0.42
    Charging
    0.41
    AMBI
    0.40
    charging
    0.38
    カテゴリ
    0.38
    UCLE
    0.37
     Categories
    0.35
    Categories
    0.35
    hattis
    0.35
    ";//
    0.34
    Act Density 0.002%

    No Known Activations