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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical or statistical notation

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

    special characters and markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.78
     Мексичка
    -0.70
     مرئيه
    -0.68
    󠁣
    -0.68
     defaultstate
    -0.60
    tanleria
    -0.55
     AssemblyCulture
    -0.54
    oredCriteria
    -0.53
    amoan
    -0.52
    ">—
    -0.52
    POSITIVE LOGITS
    TokenNameLPAREN
    0.49
    TokenNameLBRACE
    0.47
    TokenNameL
    0.43
    TokenNameRPAREN
    0.42
     Mexique
    0.40
     nonUne
    0.39
    codecSelfer
    0.35
    sufficiency
    0.33
     Pfeiffer
    0.33
    Yess
    0.32
    Act Density 0.571%

    No Known Activations