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

    Neuronpedia

    INDEX
    Explanations

    certainly followed by affirmation or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     that
    1.16
     with
    1.08
     by
    1.05
     (
    1.00
     which
    0.96
    ك
    0.95
    ERVER
    0.90
    ουν
    0.88
    ب
    0.88
     of
    0.87
    POSITIVE LOGITS
    in
    1.09
     certainly
    1.03
    Certainly
    0.97
     Certainly
    0.88
     обратить
    0.77
    ।
    0.73
    appears
    0.73
    。
    0.72
    。",
    0.71
    ᱘
    0.70
    Act Density 0.002%

    No Known Activations