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

    Neuronpedia

    INDEX
    Explanations

    tech company urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    3.14
    pe
    2.67
    ,,,
    2.28
    it
    2.22
    S
    2.15
    ما
    2.15
    Kp
    2.12
     p
    2.08
    rest
    2.08
    en
    2.04
    POSITIVE LOGITS
    ો
    2.85
    нгтон
    2.71
    ी
    2.69
    san
    2.67
    ्स
    2.64
    smanship
    2.55
    ׁ
    2.52
    СТЬ
    2.46
    খাস্ত
    2.39
     hémorro
    2.34
    Act Density 1.236%

    No Known Activations