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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or states related to existence or specificity

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

    even if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerade
    -0.63
     jspb
    -0.56
    tagHelperRunner
    -0.56
     oprot
    -0.55
     fieldNum
    -0.54
    hyrchwyd
    -0.52
     Chwiliwch
    -0.52
    ंदीखरीदारी
    -0.50
    RTSC
    -0.50
     ModelExpression
    -0.49
    POSITIVE LOGITS
     sekal
    0.63
    yntaxException
    0.56
     argint
    0.52
     schoenen
    0.49
    就算
    0.49
    就算是
    0.47
    哪怕
    0.45
     akár
    0.44
     mijne
    0.44
    huur
    0.44
    Act Density 0.024%

    No Known Activations