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

    Neuronpedia

    INDEX
    Explanations

    identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rms
    -0.08
    ᵑ
    -0.07
    artisan
    -0.07
     Tháng
    -0.07
    Driver
    -0.07
    -training
    -0.07
    _sign
    -0.07
    noch
    -0.07
    馏
    -0.06
     incom
    -0.06
    POSITIVE LOGITS
     יור
    0.07
    讚
    0.07
    ᕚ
    0.07
    推送
    0.07
    ければ
    0.07
    .ToBoolean
    0.06
    _CO
    0.06
     غالب
    0.06
     السياس
    0.06
     הישרא
    0.06
    Act Density 0.004%

    No Known Activations