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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الشم
    -0.06
    QUOTE
    -0.06
     srp
    -0.06
    _TRANS
    -0.06
     alan
    -0.06
    (ne
    -0.06
    $ar
    -0.06
     Reign
    -0.06
     tornado
    -0.06
    hot
    -0.06
    POSITIVE LOGITS
     فرمود
    0.07
     flashed
    0.07
     (/
    0.07
    蜘蛛词
    0.07
     notorious
    0.07
    ;color
    0.06
     tant
    0.06
     اخت
    0.06
    就在
    0.06
     glUniform
    0.06
    Act Density 0.000%

    No Known Activations