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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    你不
    -0.06
    .comm
    -0.06
    /**<
    -0.06
     urlpatterns
    -0.06
     أصحاب
    -0.06
    .Glide
    -0.06
    APS
    -0.06
    一心
    -0.06
    capt
    -0.06
     Lean
    -0.06
    POSITIVE LOGITS
    ﺌ
    0.07
     wire
    0.07
    Color
    0.07
    讽
    0.07
     string
    0.07
     IMD
    0.07
    (Text
    0.06
    %↵
    0.06
     bondage
    0.06
    box
    0.06
    Act Density 0.003%

    No Known Activations