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
     Glyph
    -0.06
     bunun
    -0.06
     commerce
    -0.06
     uptake
    -0.06
     Kingdom
    -0.06
    ission
    -0.06
     movements
    -0.06
     Cup
    -0.06
     solo
    -0.06
     residing
    -0.06
    POSITIVE LOGITS
     roadside
    0.09
    .amazonaws
    0.07
    查询
    0.07
     объ
    0.07
     {↵↵↵↵
    0.07
    SET
    0.06
    소개
    0.06
    ktop
    0.06
    .INSTANCE
    0.06
    مام
    0.06
    Act Density 0.002%

    No Known Activations