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

    Neuronpedia

    INDEX
    Explanations

    standards for products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    2.36
    ோ
    2.06
    ੇ
    2.05
    タリー
    1.93
    ב
    1.90
    ಯ
    1.85
    ur
    1.84
    களை
    1.79
    র
    1.79
    ির
    1.76
    POSITIVE LOGITS
    it
    2.13
    ۱
    2.11
     chimiques
    1.92
     Poo
    1.91
    seu
    1.86
    ndarray
    1.81
     Autres
    1.79
     hela
    1.76
    Produkt
    1.73
    us
    1.73
    Act Density 0.948%

    No Known Activations