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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     구글
    -0.07
     amidst
    -0.06
    muş
    -0.06
     حج
    -0.06
    Talking
    -0.06
    ,new
    -0.06
     Αγ
    -0.06
     tall
    -0.06
     slander
    -0.06
     shameful
    -0.06
    POSITIVE LOGITS
     ToolStrip
    0.07
     ####
    0.06
    XX
    0.06
     Falls
    0.06
    _TD
    0.06
    ीछ
    0.06
    PLE
    0.06
    ทย
    0.06
    (stmt
    0.06
    砲
    0.06
    Act Density 0.027%

    No Known Activations