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

    Neuronpedia

    INDEX
    Explanations

    explaining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SBC
    -0.09
     ঘৰ
    -0.08
    (GLFW
    -0.08
     ք
    -0.08
     lyk
    -0.08
     البيت
    -0.08
     لقب
    -0.08
     مي
    -0.08
     柏
    -0.08
     मालिक
    -0.08
    POSITIVE LOGITS
     подробно
    0.08
     aloud
    0.08
     jednotliv
    0.08
     thoroughly
    0.08
     anlat
    0.08
     exposition
    0.08
    �
    0.07
     verbosity
    0.07
     approfond
    0.07
    ove
    0.07
    Act Density 0.020%

    No Known Activations