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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief or speculation

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

    believed to have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amaño
    -0.52
    paravant
    -0.52
    IndentedString
    -0.47
    terday
    -0.45
    immediately
    -0.44
     Enfin
    -0.44
    AsUp
    -0.43
    anmoins
    -0.43
     conosco
    -0.42
     ویکی‌پدی
    -0.42
    POSITIVE LOGITS
    istoitu
    0.45
     Audiodateien
    0.45
    Portale
    0.44
    Билгалдахарш
    0.43
    /**
    0.43
     reputed
    0.41
    sproz
    0.41
    Slf
    0.39
     promoc
    0.39
    kaŭ
    0.39
    Act Density 0.061%

    No Known Activations