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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getDouble
    -0.08
     fatto
    -0.07
     فإذا
    -0.07
     tooltips
    -0.07
     PdfPCell
    -0.07
    有更多的
    -0.06
    //================================================================
    -0.06
     безоп
    -0.06
    MaxLength
    -0.06
     slender
    -0.06
    POSITIVE LOGITS
    promise
    0.07
     undergoing
    0.07
    吐槽
    0.07
    _nom
    0.07
     suicide
    0.07
    耐
    0.07
    	mouse
    0.07
    工信
    0.07
    رصد
    0.06
    性能
    0.06
    Act Density 0.019%

    No Known Activations