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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, whitespace, and structural elements in text

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

    mathematical expressions and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     désolés
    -0.50
     autorytatywna
    -0.48
     Bioaccumulative
    -0.46
     Normdatei
    -0.45
     wikipagina
    -0.45
    setObjectName
    -0.39
     pewno
    -0.38
    ieteur
    -0.38
    UpInside
    -0.37
     werking
    -0.36
    POSITIVE LOGITS
    UnusedPrivate
    0.70
    
    0.54
    pushFollow
    0.53
    exitRule
    0.52
     للمعارف
    0.52
    DeleteBehavior
    0.49
    หวัด
    0.47
    SourceChecksum
    0.47
     UIAlert
    0.47
     ConstraintSet
    0.47
    Act Density 0.001%

    No Known Activations