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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    criminal
    -0.07
    fieldName
    -0.06
    ``,
    -0.06
     ва
    -0.06
     кто
    -0.06
    (jQuery
    -0.06
    ��
    -0.06
    ，却
    -0.06
     Льв
    -0.06
     подход
    -0.06
    POSITIVE LOGITS
     Moor
    0.14
     Mori
    0.10
     More
    0.07
    unding
    0.07
     Kauf
    0.07
     Docs
    0.07
    대한
    0.06
    -example
    0.06
    ільш
    0.06
    oro
    0.06
    Act Density 0.009%

    No Known Activations