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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    谓
    -0.08
     anno
    -0.07
    Boolean
    -0.07
    Because
    -0.07
    向
    -0.07
    -res
    -0.07
    称为
    -0.07
    icl
    -0.07
     ain
    -0.07
    /preferences
    -0.07
    POSITIVE LOGITS
     shower
    0.07
    ᗷ
    0.07
    Ө
    0.07
    十字
    0.07
     Liberia
    0.07
     Solomon
    0.07
    腩
    0.07
     Lots
    0.07
    戮
    0.06
     Ч
    0.06
    Act Density 0.002%

    No Known Activations