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

    Neuronpedia

    INDEX
    Explanations

    Mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _COLUMN
    -0.09
    /categories
    -0.07
    /category
    -0.07
    flower
    -0.07
    'description
    -0.07
    无需
    -0.07
    _ROW
    -0.07
    ลีก
    -0.07
    *num
    -0.07
    .Category
    -0.07
    POSITIVE LOGITS
     itd
    0.08
     Bida
    0.08
     Quito
    0.08
     Apar
    0.08
     ।↵↵
    0.07
     알아
    0.07
     naka
    0.07
    .’↵↵
    0.07
    iria
    0.07
     secure
    0.07
    Act Density 0.023%

    No Known Activations