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

    Neuronpedia

    INDEX
    Explanations

    fragments of code or programming constructs

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

    computer code and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Atlántico
    -0.49
    ScopeManager
    -0.48
     gré
    -0.41
     Cientí
    -0.41
     Australien
    -0.40
     käyttö
    -0.40
     sähkö
    -0.40
     grecque
    -0.40
     Zivil
    -0.39
     Wachs
    -0.39
    POSITIVE LOGITS
    +:+
    0.89
    <?
    0.80
    BagLayout
    0.80
    apunov
    0.71
     stmt
    0.68
     виправивши
    0.66
    abbix
    0.65
     defaultstate
    0.64
     '{@
    0.63
     ModelExpression
    0.59
    Act Density 0.009%

    No Known Activations