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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating quantities or relationships

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

    dark themedark themesdark mode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jā
    -0.36
     parís
    -0.33
     inneces
    -0.31
     Partager
    -0.31
     Détails
    -0.30
    ūrė
    -0.30
     jaula
    -0.30
     compét
    -0.30
     esmeralda
    -0.30
     sanitaires
    -0.29
    POSITIVE LOGITS
    findpost
    0.66
    GEBURTS
    0.64
    libft
    0.63
    LEncoder
    0.54
    orianCalendar
    0.50
    ⟭
    0.50
     seaborn
    0.48
    帖最后由
    0.48
    出版年
    0.48
    KommentareTeilen
    0.47
    Act Density 0.000%

    No Known Activations