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

    Neuronpedia

    INDEX
    Explanations

    code processing/parsing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Executive
    -0.07
    Alan
    -0.07
     nuts
    -0.07
     Palestin
    -0.07
     democrat
    -0.07
    χεία
    -0.06
     arteries
    -0.06
     Suicide
    -0.06
    启动
    -0.06
     anth
    -0.06
    POSITIVE LOGITS
    -blog
    0.07
     ฟ
    0.06
    uchs
    0.06
     Cooking
    0.06
    ською
    0.06
    /page
    0.06
    845
    0.06
     windowHeight
    0.06
    건
    0.06
    _CHARACTER
    0.06
    Act Density 0.009%

    No Known Activations