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

    Neuronpedia

    INDEX
    Explanations

    probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grated
    -0.09
    lates
    -0.08
    ុក
    -0.08
    .Margin
    -0.08
    umen
    -0.08
    Dental
    -0.08
    ditch
    -0.07
     diversité
    -0.07
    iumi
    -0.07
    dej
    -0.07
    POSITIVE LOGITS
     बनाने
    0.09
     बन
    0.09
     ఎక్కువ
    0.08
     बजाय
    0.08
     либо
    0.08
     प्रतियोग
    0.08
    -than
    0.08
     Robots
    0.07
     exceeded
    0.07
    人与
    0.07
    Act Density 0.010%

    No Known Activations