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

    Neuronpedia

    INDEX
    Explanations

    comments or annotations within code

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

    code blocks and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.90
     Chwiliwch
    -0.68
    RenderAtEndOf
    -0.66
    WaitGroup
    -0.58
    parsedMessage
    -0.57
     <>",
    -0.57
    WireFormatLite
    -0.56
    RuleContext
    -0.55
     '\\;'
    -0.53
     Numerade
    -0.52
    POSITIVE LOGITS
     mijne
    0.46
     avoided
    0.45
     ettei
    0.43
     genoeg
    0.43
     avoidable
    0.43
     oublier
    0.42
     lijst
    0.41
     gwia
    0.41
     suficientes
    0.41
     toekomst
    0.40
    Act Density 0.072%

    No Known Activations