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

    Neuronpedia

    INDEX
    Explanations

    references to film critics and their reviews

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

    Followed by names or dates

    np_acts-logits-general · gemini-2.0-flash

    critic names after "including" or "by"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.53
     apprend
    -0.47
     trị
    -0.45
    preneurship
    -0.45
    uscular
    -0.44
    łys
    -0.42
    jacency
    -0.42
    IVersion
    -0.42
     HttpNotFound
    -0.41
    ppuden
    -0.41
    POSITIVE LOGITS
     review
    2.74
     reviews
    2.44
    review
    2.42
     Review
    2.35
    Review
    2.29
     reviewing
    2.28
     reviewed
    2.23
     REVIEW
    2.18
     reviewer
    2.13
     Reviews
    2.06
    Act Density 0.280%

    No Known Activations