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

    Neuronpedia

    INDEX
    Explanations

    ways, including

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ться
    0.89
    THING
    0.86
    0.81
    eper
    0.80
     diurnal
    0.80
    ق
    0.80
    %!
    0.79
    Alchemy
    0.78
    েরই
    0.78
    फर
    0.76
    POSITIVE LOGITS
    Ｐ
    0.91
    Ｉ
    0.84
    Ｄ
    0.79
    <0x93>
    0.74
    𝙸
    0.74
    z
    0.72
    ありません
    0.71
    ИА
    0.71
    <0xA0>
    0.70
     Gross
    0.70
    Act Density 0.000%

    No Known Activations