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

    Neuronpedia

    INDEX
    Explanations

    Bracketed phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sar
    -0.07
    Tweet
    -0.07
    šky
    -0.06
     INTERVAL
    -0.06
     pie
    -0.06
     municipalities
    -0.06
     工
    -0.06
    pow
    -0.06
     Polic
    -0.06
     Xin
    -0.06
    POSITIVE LOGITS
    ยก
    0.07
    /MM
    0.07
     dealt
    0.07
    getLast
    0.06
    _PK
    0.06
     року
    0.06
    ('<?
    0.06
     Massive
    0.06
    webdriver
    0.06
     coop
    0.06
    Act Density 0.013%

    No Known Activations