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

    Neuronpedia

    INDEX
    Explanations

    structured data elements or attributes in code

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

    content and getting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nacionales
    -0.54
     Keuangan
    -0.49
     polaire
    -0.48
     Aufwand
    -0.47
     Künst
    -0.47
    Literatuur
    -0.46
     Durchschnitt
    -0.46
     sorteo
    -0.46
     inalámb
    -0.45
     Teléfono
    -0.45
    POSITIVE LOGITS
     Content
    1.01
    Content
    0.97
    content
    0.97
     content
    0.92
    getContent
    0.91
     getContent
    0.84
    CONTENT
    0.81
     CONTENT
    0.79
    ontent
    0.78
    setContent
    0.71
    Act Density 0.012%

    No Known Activations