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

    Neuronpedia

    INDEX
    Explanations

    step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Math
    -0.08
    愛
    -0.07
    .runtime
    -0.07
     Classical
    -0.07
    🛁
    -0.07
     Ecc
    -0.07
    _SET
    -0.07
    cleanup
    -0.07
     renowned
    -0.07
    恪
    -0.06
    POSITIVE LOGITS
    �
    0.07
     honors
    0.07
     cables
    0.07
    -relative
    0.07
     Gespräch
    0.07
    Chars
    0.07
     braz
    0.06
    slides
    0.06
     brighter
    0.06
     mạch
    0.06
    Act Density 0.061%

    No Known Activations