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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тепер
    -0.07
    ules
    -0.07
     kỳ
    -0.06
    .localized
    -0.06
     Ames
    -0.06
    .codes
    -0.06
     ByVal
    -0.06
     숨
    -0.06
     defs
    -0.05
     cestu
    -0.05
    POSITIVE LOGITS
    ;↵↵↵↵↵
    0.07
     }}↵
    0.07
     {}),↵
    0.07
    ارب
    0.06
    );
↵
↵
↵
    0.06
     Decom
    0.06
    ;↵↵↵↵
    0.06
     negotiate
    0.06
     stumbling
    0.06
              ↵
    0.06
    Act Density 0.178%

    No Known Activations