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

    Neuronpedia

    INDEX
    Explanations

    legal statutes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -bo
    -0.07
     discipl
    -0.07
    陽
    -0.06
    abytes
    -0.06
    Automatic
    -0.06
    avier
    -0.06
    _motor
    -0.06
     EQUAL
    -0.06
     Billy
    -0.06
     اختل
    -0.06
    POSITIVE LOGITS
     사망
    0.07
    .Ge
    0.07
    .pdf
    0.07
    。”↵↵
    0.06
     Jama
    0.06
     απο
    0.06
    誤
    0.06
    .raise
    0.06
    utorials
    0.06
     besar
    0.06
    Act Density 0.003%

    No Known Activations