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

    Neuronpedia

    INDEX
    Explanations

    ul

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _even
    -0.08
    víc
    -0.07
     Marvin
    -0.06
     Beginner
    -0.06
    ,right
    -0.06
     tập
    -0.06
     fundamentally
    -0.06
     มหาว
    -0.06
    yclopedia
    -0.06
     Kami
    -0.06
    POSITIVE LOGITS
     sul
    0.07
     disability
    0.07
     Sul
    0.07
    ún
    0.07
    �
    0.06
     thất
    0.06
    777
    0.06
    ΑΝ
    0.06
     thaw
    0.06
     restaur
    0.06
    Act Density 0.004%

    No Known Activations