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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation marks and certain formatting symbols

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

    [ or ) followed by code/numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.53
    Ӕ
    -0.52
    PutMapping
    -0.48
     Autorizaciones
    -0.45
    rungsseite
    -0.44
    NameInMap
    -0.44
     opge
    -0.42
    ENOMEM
    -0.42
    ंदीखरीदारी
    -0.42
     Lag
    -0.40
    POSITIVE LOGITS
    appartamento
    0.44
    Seni
    0.42
    ftagPool
    0.41
     Gegenteil
    0.39
    ConstraintMaker
    0.38
    parsedMessage
    0.38
     merek
    0.37
    mappedBy
    0.37
    SequentialGroup
    0.37
    Biografía
    0.37
    Act Density 0.144%

    No Known Activations