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

    Neuronpedia

    INDEX
    Explanations

    would

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .djangoproject
    -0.07
     Team
    -0.07
     lí
    -0.07
     avoid
    -0.07
     Abb
    -0.07
    /git
    -0.07
     kla
    -0.07
     Gam
    -0.07
     Traits
    -0.07
     superhero
    -0.06
    POSITIVE LOGITS
     writings
    0.08
     unborn
    0.07
    云端
    0.07
     manually
    0.07
    暲
    0.07
    总局
    0.07
    فرح
    0.07
     crafted
    0.07
     danced
    0.07
    _tabs
    0.07
    Act Density 0.019%

    No Known Activations