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

    Neuronpedia

    INDEX
    Explanations

    deck building

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ત્મક
    2.73
    ться
    2.71
    amed
    2.60
     deterior
    2.58
     stature
    2.58
    েবের
    2.57
    paused
    2.56
    ে
    2.56
    pygame
    2.54
     iyo
    2.53
    POSITIVE LOGITS
     irony
    3.31
    ل
    3.30
     notables
    2.91
    KeyPressed
    2.78
    tól
    2.76
     brink
    2.71
    ä
    2.65
     Gł
    2.61
    ята
    2.60
    başı
    2.60
    Act Density 0.005%

    No Known Activations