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

    Neuronpedia

    INDEX
    Explanations

    formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kud
    -0.07
     Boulder
    -0.07
     فقط
    -0.06
     Subjects
    -0.06
    ertil
    -0.06
    ='%
    -0.06
    /lang
    -0.06
    _Struct
    -0.06
     نقش
    -0.06
     softer
    -0.06
    POSITIVE LOGITS
    lias
    0.07
    ,s
    0.07
     Programming
    0.06
    -bl
    0.06
    _pass
    0.06
    (_
    0.06
    �
    0.06
     judged
    0.06
    (em
    0.06
     GTX
    0.06
    Act Density 0.020%

    No Known Activations