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

    Neuronpedia

    INDEX
    Explanations

    references to legendary or mythical figures and themes related to power

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

    followed by punctuation or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    programming, SQL, and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.63
    HasForeignKey
    -0.62
    \{\\
    -0.62
     propOrder
    -0.61
    DeleteBehavior
    -0.55
    بوابة
    -0.54
    })}\
    -0.54
    '),
    -0.52
    )))
    -0.52
    NewUrlParser
    -0.51
    POSITIVE LOGITS
     everybody
    0.66
     oneself
    0.64
     bibliographical
    0.64
     again
    0.60
     somebody
    0.60
     be
    0.59
     comprise
    0.57
     owing
    0.56
    Somebody
    0.56
     asemenea
    0.55
    Act Density 0.164%

    No Known Activations