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

    Neuronpedia

    INDEX
    Explanations

    youtube urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ení
    1.21
     riqueza
    1.17
     Já
    1.16
    都有
    1.15
     ocor
    1.14
    LOSS
    1.14
    AN
    1.13
    ргани
    1.13
     อ่าน
    1.13
    寿命
    1.12
    POSITIVE LOGITS
    a
    1.82
    د
    1.76
    ی
    1.61
    न
    1.49
    ને
    1.48
    в
    1.46
    s
    1.43
    ת
    1.41
    ו
    1.34
    ス
    1.34
    Act Density 0.005%

    No Known Activations