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

    Neuronpedia

    INDEX
    Explanations

    advantages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    がお
    -0.07
     ownership
    -0.07
    stories
    -0.07
    来了
    -0.06
     सद
    -0.06
    .testing
    -0.06
     Svg
    -0.06
    SW
    -0.06
    洪
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    (Main
    0.07
     준비
    0.07
    hetic
    0.06
     Goku
    0.06
    merge
    0.06
    itelné
    0.06
    네요
    0.06
    _uint
    0.06
     deactivated
    0.06
    εύ
    0.06
    Act Density 0.001%

    No Known Activations