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
    colour
    -0.07
    UEST
    -0.07
     Campbell
    -0.07
    .extern
    -0.07
    溴
    -0.06
     prosperous
    -0.06
    .writeString
    -0.06
     disp
    -0.06
    合い
    -0.06
    _PRIV
    -0.06
    POSITIVE LOGITS
    骨头
    0.08
    Updates
    0.07
     Paths
    0.07
    回到了
    0.07
    Ệ
    0.07
    /Internal
    0.07
     lẽ
    0.07
    ection
    0.07
     menus
    0.07
     KeyValue
    0.07
    Act Density 0.007%

    No Known Activations