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

    Neuronpedia

    INDEX
    Explanations

    Standards numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ीआई
    -0.06
     chỗ
    -0.06
     contador
    -0.06
     пери
    -0.06
    528
    -0.06
    #SBATCH
    -0.06
     Fahrenheit
    -0.06
    _Select
    -0.06
    -Benz
    -0.06
    .mapper
    -0.06
    POSITIVE LOGITS
    伤
    0.06
    였다
    0.06
     dramas
    0.06
     взрос
    0.06
    ategorized
    0.06
    usted
    0.06
     byste
    0.06
    encil
    0.06
    ‌تواند
    0.06
    lam
    0.06
    Act Density 0.010%

    No Known Activations