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

    Neuronpedia

    INDEX
    Explanations

    holidays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    -2.52
    erintah
    -2.45
    lewati
    -2.39
     Anſ
    -2.28
     bahwa
    -2.23
    趼
    -2.19
     htmlFor
    -2.16
    ).
    -2.13
    PreExecute
    -2.09
    ā
    -2.08
    POSITIVE LOGITS
     holidays
    2.86
    髏
    2.48
    of
    2.42
     jokes
    2.31
    秾
    2.28
    茈
    2.25
    2.23
    镞
    2.22
    圌
    2.20
     accolades
    2.19
    Act Density 0.005%

    No Known Activations