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

    Neuronpedia

    INDEX
    Explanations

    block

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Icon
    -0.07
    HA
    -0.07
    ερμαν
    -0.07
     दक
    -0.07
    antaged
    -0.06
    ุษ
    -0.06
    You
    -0.06
     청
    -0.06
    country
    -0.06
    卢
    -0.06
    POSITIVE LOGITS
    ,)↵
    0.07
     +/-
    0.06
     buck
    0.06
    нул
    0.06
     '/'↵
    0.06
     ib
    0.06
    _CANCEL
    0.06
     financier
    0.06
     dlg
    0.06
     Banc
    0.06
    Act Density 0.001%

    No Known Activations