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

    Neuronpedia

    INDEX
    Explanations

    math inequalities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _IMPL
    -0.07
    isposable
    -0.06
    _wrapper
    -0.06
     JsonConvert
    -0.06
     epile
    -0.06
    videos
    -0.06
     BITS
    -0.06
     webinar
    -0.06
     "";
↵
    -0.06
     잡담
    -0.06
    POSITIVE LOGITS
    ­
    0.07
     Knee
    0.07
     relação
    0.07
     kişiler
    0.07
     funciones
    0.06
     euth
    0.06
     zamanda
    0.06
     und
    0.06
    收益
    0.06
     */
↵
↵
    0.06
    Act Density 0.005%

    No Known Activations