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

    Neuronpedia

    INDEX
    Explanations

    string formatting functions in code syntax

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

    string formatting with `%`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.91
    hoeddwyd
    -0.63
     мәкал
    -0.63
    EndProject
    -0.60
    __(/*!
    -0.60
    новниш
    -0.56
    )*/
    -0.55
    parsedMessage
    -0.55
     geſch
    -0.55
    exitRule
    -0.54
    POSITIVE LOGITS
    WithFormat
    0.69
     adanya
    0.32
     dimiliki
    0.29
    Etimo
    0.28
    Hvordan
    0.28
    @
    0.28
    encji
    0.28
     hvem
    0.27
    OMO
    0.27
    isEqualTo
    0.27
    Act Density 0.005%

    No Known Activations