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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arizona
    -0.06
    事
    -0.06
     OBS
    -0.06
     lots
    -0.06
     أنا
    -0.06
     Mog
    -0.06
     spoil
    -0.06
     Websites
    -0.06
    SJ
    -0.06
     capita
    -0.06
    POSITIVE LOGITS
    hc
    0.07
     　 　
    0.06
     مشکل
    0.06
     نماز
    0.06
    _copy
    0.06
    [list
    0.06
    odge
    0.06
    ascal
    0.06
    restrial
    0.06
    わたし
    0.06
    Act Density 0.000%

    No Known Activations