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

    Neuronpedia

    INDEX
    Explanations

    which is or means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.81
     zdję
    0.79
     rodzaj
    0.78
     usato
    0.75
    นุ
    0.73
    \<^
    0.73
     marchio
    0.73
    नपुर
    0.72
     alakalı
    0.72
     راجسټریشن
    0.71
    POSITIVE LOGITS
     (
    0.90
     in
    0.89
    خ
    0.81
    ల
    0.80
    عي
    0.79
    Z
    0.79
    ing
    0.79
    ين
    0.77
    是将
    0.75
    K
    0.75
    Act Density 0.064%

    No Known Activations