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

    Neuronpedia

    INDEX
    Explanations

    negative or contradictory statements and their related implications

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

    negation or absence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enderror
    -0.59
     فريبيس
    -0.56
    esModule
    -0.54
    ChildScrollView
    -0.44
    IDENTS
    -0.43
    CloseOperation
    -0.42
     winning
    -0.41
    succ
    -0.41
     Abr
    -0.40
     Burrows
    -0.40
    POSITIVE LOGITS
    RTDA
    0.42
    parsedMessage
    0.41
     duquel
    0.40
     niega
    0.40
    Externé
    0.40
     slowest
    0.40
    TryDecodeAsNil
    0.40
    (!__
    0.40
     wikipagina
    0.39
     tearDown
    0.38
    Act Density 0.153%

    No Known Activations