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

    Neuronpedia

    INDEX
    Explanations

    programming keywords declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     teraz
    0.75
    final
    0.75
    valueOf
    0.75
    dua
    0.72
    cop
    0.70
     final
    0.70
     miesz
    0.69
    ոչ
    0.69
     stent
    0.69
    angsa
    0.69
    POSITIVE LOGITS
     foreach
    1.42
    foreach
    1.41
     string
    1.04
    string
    0.96
     bool
    0.95
     IEnumerable
    0.87
    bool
    0.85
    IEnumerable
    0.85
     每
    0.77
    ಳೆಯ
    0.77
    Act Density 0.137%

    No Known Activations