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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Z
    -0.07
    critical
    -0.07
    odic
    -0.06
    vp
    -0.06
     Infrastructure
    -0.06
    DEN
    -0.06
    c
    -0.06
     سف
    -0.06
    アン
    -0.06
     дня
    -0.06
    POSITIVE LOGITS
     Tropical
    0.07
     novo
    0.06
    autical
    0.06
     captures
    0.06
     شیمی
    0.06
    (clazz
    0.06
     kostenlos
    0.06
     enim
    0.06
    Philip
    0.06
     ◄
    0.06
    Act Density 0.083%

    No Known Activations