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

    Neuronpedia

    INDEX
    Explanations

    Random characters/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Performs
    -0.07
    _FLAG
    -0.06
    족
    -0.06
     χ
    -0.06
     Tos
    -0.06
    .false
    -0.06
     chức
    -0.06
     holder
    -0.06
     rods
    -0.06
    _app
    -0.06
    POSITIVE LOGITS
    yntaxException
    0.06
    yonel
    0.06
    <Renderer
    0.06
    阻
    0.06
    okay
    0.06
    SCALL
    0.06
    adge
    0.06
    리는
    0.06
    ประโยชน
    0.06
    ��
    0.06
    Act Density 0.364%

    No Known Activations