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

    Neuronpedia

    INDEX
    Explanations

    Hardness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     URLs
    -0.08
     Monument
    -0.08
     Improving
    -0.07
    _daily
    -0.07
    ort
    -0.07
     constexpr
    -0.07
     diária
    -0.07
     simplifying
    -0.07
     Steel
    -0.07
     Heavenly
    -0.07
    POSITIVE LOGITS
     وغ
    0.08
     recessed
    0.08
     trough
    0.08
     തേ
    0.08
     оцен
    0.07
     تركيب
    0.07
     bestowed
    0.07
     trustees
    0.07
    طبيق
    0.07
     ért
    0.07
    Act Density 0.002%

    No Known Activations