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

    Neuronpedia

    INDEX
    Explanations

    classification by type or kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wohner
    0.71
     किसान
    0.69
     लॉकडाउन
    0.69
    歌詞
    0.68
     किसानों
    0.67
     მიმოწერა
    0.64
     embar
    0.64
    Padding
    0.63
    ர்கள்
    0.63
    塚
    0.61
    POSITIVE LOGITS
     types
    3.31
     type
    3.25
    类型
    3.12
     genres
    2.93
     tipo
    2.85
    类型的
    2.83
     tipos
    2.82
    type
    2.81
     jenis
    2.81
     Types
    2.77
    Act Density 4.823%

    No Known Activations