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

    Neuronpedia

    INDEX
    Explanations

    Journalism/publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ουλίου
    -0.06
    IBLE
    -0.06
     liquid
    -0.06
    内容
    -0.06
    �i
    -0.06
    -product
    -0.06
    _SIDE
    -0.06
    巡
    -0.06
     mercy
    -0.06
    十二
    -0.06
    POSITIVE LOGITS
     adip
    0.07
    端
    0.06
     sle
    0.06
    اضي
    0.06
    лях
    0.06
    (lambda
    0.06
     Tested
    0.06
    �
    0.06
    "][
    0.06
    .comboBox
    0.06
    Act Density 0.019%

    No Known Activations