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

    Neuronpedia

    INDEX
    Explanations

    Using tools

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ाइड
    -0.07
     نبود
    -0.07
    ‌آ
    -0.07
    ाँ
    -0.06
     campus
    -0.06
    ーフ
    -0.06
    _name
    -0.06
    -Level
    -0.06
    Site
    -0.06
     reproduced
    -0.06
    POSITIVE LOGITS
     Affero
    0.07
     leider
    0.07
     Prem
    0.07
    03
    0.06
    accepted
    0.06
    _detector
    0.06
     суще
    0.06
     Những
    0.06
    сяч
    0.06
     akci
    0.06
    Act Density 0.061%

    No Known Activations