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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures and function definitions in programming code

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

    closing brackets and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.35
     autorités
    -0.35
     fhort
    -0.33
    dialement
    -0.32
     pouvoirs
    -0.32
    Help
    -0.32
     élevées
    -0.32
     fubject
    -0.31
     himſelf
    -0.31
     Berührung
    -0.30
    POSITIVE LOGITS
     endwhile
    0.68
    الحياه
    0.66
     ExecuteAsync
    0.63
    endforeach
    0.62
    Jeografia
    0.59
    ArrowToggle
    0.58
    preduce
    0.57
    >[]
    0.56
     postIndex
    0.55
     ***!
    0.55
    Act Density 0.016%

    No Known Activations