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

    Neuronpedia

    INDEX
    Explanations

    website deployment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seminar
    -0.08
     rais
    -0.08
    defined
    -0.08
     numerical
    -0.08
    weekday
    -0.08
     süm
    -0.07
     kaž
    -0.07
    vehicles
    -0.07
    numer
    -0.07
    roupe
    -0.07
    POSITIVE LOGITS
    无需
    0.10
     klik
    0.10
     Spins
    0.10
     Бесплат
    0.09
     点击
    0.09
     effortless
    0.09
    .git
    0.09
     ücretsiz
    0.09
     Shorts
    0.09
     自动
    0.08
    Act Density 0.001%

    No Known Activations