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

    Neuronpedia

    INDEX
    Explanations

    places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ie
    -0.91
     Nor
    -0.90
     vit
    -0.67
    Nor
    -0.67
    i
    -0.66
     cla
    -0.62
    ed
    -0.59
    e
    -0.58
     i
    -0.57
    vit
    -0.54
    POSITIVE LOGITS
     Majefty
    1.05
     engraçadas
    0.96
     Efq
    0.96
    RenderAtEndOf
    0.94
     Jefus
    0.92
     فريبيس
    0.90
     myſelf
    0.87
     ſche
    0.86
     varandra
    0.86
     Eſ
    0.86
    Act Density 1.309%

    No Known Activations