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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mar , Dorr , hib

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     timeType
    -0.41
     digna
    -0.40
    detectChanges
    -0.39
    \}^{
    -0.38
     lote
    -0.38
    VENT
    -0.37
    melt
    -0.37
     Tide
    -0.36
    echt
    -0.35
     Paglinawan
    -0.35
    POSITIVE LOGITS
     שוליים
    0.60
     Chwiliwch
    0.59
    发表于
    0.58
    IntoConstraints
    0.57
     autorytatywna
    0.57
     MainAxisSize
    0.56
     Mar
    0.55
    Mar
    0.54
     ویکی‌پدیا
    0.54
     Gar
    0.53
    Act Density 0.039%

    No Known Activations