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

    Neuronpedia

    INDEX
    Explanations

    references to news organizations and reporting

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

    news reporting and media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verifyException
    -0.59
    parsedMessage
    -0.52
    -0.52
    getDoctrine
    -0.49
     pleaſure
    -0.47
    liferay
    -0.46
    wpi
    -0.45
     TextAlign
    -0.45
    housie
    -0.44
    قایناق‌لار
    -0.44
    POSITIVE LOGITS
     reporters
    0.45
     broke
    0.44
     reporter
    0.40
    broke
    0.39
     reported
    0.38
    EndInit
    0.38
    Broke
    0.36
     mesmas
    0.36
     Broke
    0.35
     artykuł
    0.35
    Act Density 0.023%

    No Known Activations