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

    Neuronpedia

    INDEX
    Explanations

    specific function or method calls in programming contexts

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

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.32
    mado
    -0.32
     مر
    -0.32
    ment
    -0.31
    Cordialement
    -0.31
    ülés
    -0.31
     Région
    -0.31
    ness
    -0.30
    メント
    -0.30
    ート
    -0.29
    POSITIVE LOGITS
     propOrder
    0.86
    Diweddarwch
    0.78
    SharedDtor
    0.78
    encodeWith
    0.75
    principalColumn
    0.75
    AISSEE
    0.73
    verifyException
    0.70
     Italijanski
    0.69
    oneofs
    0.68
     otomatig
    0.68
    Act Density 0.001%

    No Known Activations