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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endif
    -0.27
    agger
    -0.26
    edom
    -0.26
     Æ¡n
    -0.26
    ema
    -0.26
    sem
    -0.26
    产ä¸ļ
    -0.26
    emy
    -0.25
    .pk
    -0.25
    acks
    -0.24
    POSITIVE LOGITS
    åħļæĢ»æĶ¯
    0.27
    ç²¾çĽĬ
    0.26
    éĢł
    0.26
    åĽ¢ç»ĵ
    0.26
    æĢ»æĶ¶åħ¥
    0.25
    å¸ĤåĮº
    0.25
    èĥ´
    0.24
    ResultsController
    0.24
    option
    0.24
    该éĻ¢
    0.23
    Act Density 0.018%

    No Known Activations