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

    Neuronpedia

    INDEX
    Explanations

    extension

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Author
    -0.07
    Distance
    -0.07
    מוזיקה
    -0.07
     الاتحاد
    -0.06
    Խ
    -0.06
    Boolean
    -0.06
     murdered
    -0.06
    受影响
    -0.06
    视
    -0.06
     Alvarez
    -0.06
    POSITIVE LOGITS
    诫
    0.07
    рад
    0.07
    婪
    0.07
    芥
    0.07
    ">(
    0.07
    春
    0.06
     browsing
    0.06
    SKU
    0.06
     ecx
    0.06
     bây
    0.06
    Act Density 0.022%

    No Known Activations