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

    Neuronpedia

    INDEX
    Explanations

    instances of comparative or relational expressions

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

    date ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.57
     مشين
    -0.50
     Италијани
    -0.48
    WithIOException
    -0.46
    -0.43
     Absicht
    -0.43
     eenige
    -0.41
     Italijanski
    -0.41
    Personendaten
    -0.40
    rungsseite
    -0.40
    POSITIVE LOGITS
     Curtain
    0.48
    orsese
    0.48
    errHandler
    0.43
     curt
    0.43
    テンツ
    0.43
    EndContext
    0.42
    itattu
    0.41
    RTDA
    0.40
     kur
    0.39
    quelize
    0.39
    Act Density 0.023%

    No Known Activations