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

    Neuronpedia

    INDEX
    Explanations

    constructor parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    1.00
    u
    0.94
    тин
    0.89
    המ
    0.88
    𝓪
    0.84
     shilling
    0.84
    न
    0.83
    BarButtonItem
    0.82
    น
    0.81
    Zb
    0.81
    POSITIVE LOGITS
    ’
    0.97
    ،
    0.97
    ।
    0.90
    ania
    0.89
    ೂರ್ವ
    0.86
    ispielsweise
    0.85
     siguiente
    0.83
    ierend
    0.83
     añadido
    0.81
     acúst
    0.80
    Act Density 0.000%

    No Known Activations