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

    Neuronpedia

    INDEX
    Explanations

    numbers and currency units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мастера
    1.95
     morphism
    1.85
     profesión
    1.77
    Gruß
    1.74
     человеку
    1.71
     crónica
    1.71
     subray
    1.70
     perteneciente
    1.67
    SecurityMarks
    1.66
     términos
    1.65
    POSITIVE LOGITS
    ל
    2.48
    са
    2.22
    ה
    2.11
    ن
    1.95
    ס
    1.90
    ב
    1.76
    j
    1.64
    ان
    1.62
    k
    1.57
     anciennes
    1.52
    Act Density 0.637%

    No Known Activations