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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    。
    0.87
    ay
    0.82
    ли
    0.82
    ون
    0.76
     событий
    0.76
    ﺗ
    0.76
    ა
    0.76
     Toen
    0.75
    к
    0.73
    ﺑ
    0.73
    POSITIVE LOGITS
    ührung
    0.76
    ̀ng
    0.73
    دين
    0.70
     niên
    0.70
    IBLE
    0.69
     पढ़ा
    0.68
    mothers
    0.68
    jewelry
    0.68
     utilizza
    0.67
    িকপ্ট
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.