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

    Neuronpedia

    INDEX
    Explanations

    text format specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Interestingly
    0.77
     When
    0.76
    It
    0.68
    İ
    0.68
     It
    0.67
     她
    0.67
    Interestingly
    0.67
    When
    0.66
     During
    0.65
     Она
    0.65
    POSITIVE LOGITS
    警戒
    0.70
    方向に
    0.60
    side
    0.57
    тного
    0.56
     fowl
    0.55
    жному
    0.55
    cip
    0.54
    ចែកចាយ
    0.53
    膯
    0.53
    sag
    0.52
    Act Density 0.013%

    No Known Activations