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

    Neuronpedia

    INDEX
    Explanations

    function and variable states in programming or software context

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

    boolean status setters and checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     de
    -0.35
     îna
    -0.34
     devoted
    -0.32
     had
    -0.31
    -
    -0.30
     not
    -0.29
     carried
    -0.28
     were
    -0.28
     masing
    -0.28
     del
    -0.27
    POSITIVE LOGITS
     propOrder
    0.91
    featureID
    0.89
    ロウィン
    0.82
    yntaxException
    0.78
    ьаж
    0.78
     TextAppearance
    0.76
     queſta
    0.76
     ddelweddau
    0.75
    Попис
    0.74
    AndEndTag
    0.73
    Act Density 0.026%

    No Known Activations