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

    Neuronpedia

    INDEX
    Explanations

    analog signal, sensor, or representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ע
    1.25
    ad
    1.00
    arın
    0.97
    in
    0.96
    ar
    0.96
    〢
    0.92
    0.86
    ly
    0.83
    arina
    0.83
    やすい
    0.82
    POSITIVE LOGITS
    ка
    1.16
    '
    1.05
     analog
    0.93
    که
    0.93
     ότι
    0.92
    기
    0.92
    "
    0.91
    ׳
    0.89
    Му
    0.89
    Produkt
    0.88
    Act Density 0.017%

    No Known Activations