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

    Neuronpedia

    INDEX
    Explanations

    class initialization attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ضا
    0.40
    شاہ
    0.40
    çar
    0.39
     =
    0.38
    çou
    0.38
    ['
    0.38
    getStudentNo
    0.38
     הוא
    0.37
    pool
    0.37
     نفسه
    0.37
    POSITIVE LOGITS
    ethi
    0.40
    えます
    0.39
    лиза
    0.39
    rizione
    0.38
    けます
    0.38
    ."},
    0.36
    ⊖
    0.36
     Behavioral
    0.36
     HttpException
    0.36
    柔軟
    0.35
    Act Density 0.005%

    No Known Activations