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

    Neuronpedia

    INDEX
    Explanations

    domain suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stabilize
    -0.06
     bowel
    -0.06
    цький
    -0.06
    _.
    -0.06
    (levels
    -0.06
     layui
    -0.06
     estava
    -0.06
    -save
    -0.06
     день
    -0.06
     payload
    -0.06
    POSITIVE LOGITS
    وسف
    0.07
    _plain
    0.07
    ائي
    0.06
    SCII
    0.06
     شهید
    0.06
     الأرض
    0.06
    Exp
    0.06
    Capital
    0.06
     jaz
    0.06
     ніж
    0.06
    Act Density 0.014%

    No Known Activations