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

    Neuronpedia

    INDEX
    Explanations

    documentation strings or comments in code

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

    creating classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    әрмәләр
    -0.50
     يتيمه
    -0.47
    لينكات
    -0.47
    Kaynakça
    -0.47
    Халык
    -0.46
     estekak
    -0.45
    Referències
    -0.44
     Normdatei
    -0.44
     QName
    -0.43
    outState
    -0.43
    POSITIVE LOGITS
    """
    0.55
    ModelAdmin
    0.48
    mura
    0.46
    Abitanti
    0.44
    class
    0.43
     """
    0.43
     invokingState
    0.42
    avis
    0.42
     &___
    0.42
    reus
    0.41
    Act Density 0.001%

    No Known Activations