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

    Neuronpedia

    INDEX
    Explanations

    comparative language that conveys performance or accuracy evaluations

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

    greater than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.87
    URLException
    -0.73
     للمعارف
    -0.69
     AssemblyCulture
    -0.67
     Anſ
    -0.66
     dieſes
    -0.65
     queſta
    -0.64
     intStringLen
    -0.64
     houſe
    -0.63
    EDEFAULT
    -0.63
    POSITIVE LOGITS
    notEmpty
    0.31
     any
    0.30
    UseVisualStyle
    0.30
    それ
    0.27
     iprot
    0.26
     lý
    0.26
     トップス
    0.26
     reduz
    0.25
    exitRule
    0.25
    empty
    0.25
    Act Density 0.144%

    No Known Activations