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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating satisfaction and connection

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

    words with diacritics or non-English origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoModerator
    -0.64
     MainAxisSize
    -0.63
    TintMode
    -0.60
    ToBounds
    -0.57
     BoxFit
    -0.53
    openConnection
    -0.52
    currentColor
    -0.52
    RectangleBorder
    -0.52
    mployment
    -0.51
     HttpNotFound
    -0.51
    POSITIVE LOGITS
    <sup>
    0.53
    lateinit
    0.50
     Kün
    0.48
     Fä
    0.45
     quæ
    0.44
    szön
    0.43
    ResumeLayout
    0.41
     Tsch
    0.40
     Knudsen
    0.40
    providecommand
    0.39
    Act Density 0.000%

    No Known Activations