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

    Neuronpedia

    INDEX
    Explanations

    keyboards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    享
    -0.07
     Net
    -0.07
     AP
    -0.06
     закуп
    -0.06
     '^
    -0.06
    Bins
    -0.06
    .Helper
    -0.06
    Ed
    -0.06
    527
    -0.06
     Zust
    -0.06
    POSITIVE LOGITS
    omy
    0.07
    undred
    0.06
     swingerclub
    0.06
     blush
    0.06
    finding
    0.06
     สำน
    0.06
     cuck
    0.06
    ọ
    0.06
    เซอร
    0.06
     (...)
    0.06
    Act Density 0.020%

    No Known Activations