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

    Neuronpedia

    INDEX
    Explanations

    specify/specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    2.39
    ます
    2.31
    ل
    1.94
    ২২
    1.91
    ดำเนิน
    1.89
     सफाया
    1.88
    ০০
    1.88
    이자
    1.88
    ند
    1.86
    𝗂
    1.84
    POSITIVE LOGITS
    iczne
    2.13
     endroits
    2.08
     तौर
    1.84
    И
    1.83
     adanya
    1.82
    ى
    1.82
     và
    1.79
     таки
    1.79
     Máy
    1.77
     Objet
    1.77
    Act Density 0.046%

    No Known Activations