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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Knife
    -0.07
     Knife
    -0.07
     chip
    -0.07
    .Exec
    -0.07
    \Container
    -0.06
    _multiply
    -0.06
    land
    -0.06
    (kv
    -0.06
     giz
    -0.06
     의
    -0.06
    POSITIVE LOGITS
    #/
    0.07
    ="'.
    0.07
    خذ
    0.06
     menacing
    0.06
     предполаг
    0.06
     انتظ
    0.06
    一般
    0.06
    ágenes
    0.05
     تنظ
    0.05
     volatile
    0.05
    Act Density 0.089%

    No Known Activations