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

    Neuronpedia

    INDEX
    Explanations

    code and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cef
    -0.07
    σκε
    -0.06
    ่าเป
    -0.06
    ')}}"
    -0.06
     "+
    -0.06
    렇게
    -0.06
    .effects
    -0.06
     Lyons
    -0.06
     progressed
    -0.06
     sleeping
    -0.06
    POSITIVE LOGITS
    ann
    0.07
    Budget
    0.06
     lunar
    0.06
     injuries
    0.06
     seas
    0.06
     jugg
    0.06
     pneum
    0.06
    财
    0.06
     арти
    0.06
     totalitarian
    0.06
    Act Density 0.000%

    No Known Activations