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

    Neuronpedia

    INDEX
    Explanations

    names of institutes and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.70
    1
    0.57
    ك
    0.46
    萛
    0.42
    oubtedly
    0.41
    ка
    0.40
     kanssa
    0.40
    as
    0.38
    تم
    0.38
    د
    0.38
    POSITIVE LOGITS
    '
    0.47
    B
    0.45
     Kı
    0.41
    ۵
    0.41
    াৰ
    0.41
    F
    0.40
    ר
    0.40
    ON
    0.40
    Grove
    0.40
     നെറ്റ്‌വർ
    0.39
    Act Density 0.053%

    No Known Activations