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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    版本
    -0.07
    事
    -0.07
    ilecek
    -0.07
    SqlCommand
    -0.07
     tastes
    -0.06
     Fans
    -0.06
     infants
    -0.06
    !)↵↵
    -0.06
     outrage
    -0.06
    -in
    -0.06
    POSITIVE LOGITS
     arousal
    0.07
     регулю
    0.06
     glamorous
    0.06
     مشهد
    0.06
     特
    0.06
    {j
    0.06
    _FEED
    0.06
     DOWNLOAD
    0.06
    .Mark
    0.06
    rador
    0.06
    Act Density 0.033%

    No Known Activations