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

    Neuronpedia

    INDEX
    Explanations

    references to reviews, courts, and economic studies

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

    legal and academic reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.39
    oa̍t
    -0.37
    getWriter
    -0.35
     채
    -0.35
    GMENT
    -0.35
     geme
    -0.35
    addImage
    -0.34
     terecht
    -0.34
     Rechnung
    -0.34
     figuring
    -0.34
    POSITIVE LOGITS
     review
    1.45
     reviewing
    1.37
     reviewed
    1.33
    review
    1.31
     Review
    1.27
     Reviewing
    1.26
    Review
    1.25
     REVIEW
    1.23
     reviews
    1.21
    reviewed
    1.16
    Act Density 0.063%

    No Known Activations