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

    Neuronpedia

    INDEX
    Explanations

    context headers descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    serir
    -0.07
    ￣｀
    -0.07
     лю
    -0.06
    Twig
    -0.06
    heard
    -0.06
    .PropertyType
    -0.06
     неї
    -0.06
    ตำ
    -0.06
     ayuda
    -0.06
    gende
    -0.06
    POSITIVE LOGITS
    concept
    0.07
     Steak
    0.06
    _favorite
    0.06
    -db
    0.06
     ole
    0.06
    $post
    0.06
     gem
    0.06
    Enable
    0.06
    instance
    0.06
     rég
    0.06
    Act Density 0.006%

    No Known Activations