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

    Neuronpedia

    INDEX
    Explanations

    dates, authors, and cancer

    np_acts-logits-general · gemini-2.5-flash-lite

    date formats in programming files and documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     intercourse
    -0.81
    Authorize
    -0.70
    镗
    -0.69
    |[]
    -0.69
     listOf
    -0.67
    yorsunuz
    -0.67
     మరి
    -0.66
    mysqli
    -0.66
    navigationItem
    -0.65
    borough
    -0.65
    POSITIVE LOGITS
    eseed
    0.63
    maglia
    0.61
    န်
    0.61
     Stufen
    0.60
     convert
    0.60
     Ed
    0.60
     Working
    0.59
     passaggio
    0.59
     خ
    0.59
     يحت
    0.59
    Act Density 0.064%

    No Known Activations