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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Join
    -0.06
    addle
    -0.06
    ì
    -0.06
     Nunes
    -0.06
     Müş
    -0.06
     //
↵
    -0.06
     rež
    -0.06
     ulus
    -0.06
    occupied
    -0.06
    チェ
    -0.06
    POSITIVE LOGITS
     olarak
    0.07
     Formatting
    0.07
    ยง
    0.07
    สาม
    0.06
    iyle
    0.06
     hostility
    0.06
     retros
    0.06
    _roi
    0.06
    CellValue
    0.06
    setBackground
    0.06
    Act Density 0.003%

    No Known Activations