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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SECTION
    -0.08
    費
    -0.08
    म
    -0.07
    ぬ
    -0.07
    め
    -0.07
     formas
    -0.07
    名稱
    -0.07
    ;/
    -0.07
    єї
    -0.06
    ellen
    -0.06
    POSITIVE LOGITS
     втор
    0.07
    (fileName
    0.07
     SALE
    0.06
    üny
    0.06
    userId
    0.06
     ق
    0.06
    nesty
    0.06
     عند
    0.06
    .atomic
    0.06
     presumed
    0.06
    Act Density 0.120%

    No Known Activations