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

    Neuronpedia

    INDEX
    Explanations

    separation and distinctness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alpine
    -0.07
     guten
    -0.07
    破门
    -0.07
    PointF
    -0.07
    رت
    -0.07
    AffineTransform
    -0.07
    谷爱
    -0.07
    auen
    -0.06
     Пер
    -0.06
    باراة
    -0.06
    POSITIVE LOGITS
    ائز
    0.07
     след
    0.07
     Sort
    0.07
    ancement
    0.07
    ?"
    0.07
    作為
    0.06
     outcomes
    0.06
    contexts
    0.06
    نزل
    0.06
    .mod
    0.06
    Act Density 0.089%

    No Known Activations