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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Snow
    -0.07
    (com
    -0.06
    -wheel
    -0.06
     mirrors
    -0.06
    .week
    -0.06
    .dis
    -0.06
    LA
    -0.06
    بی
    -0.06
     ब
    -0.06
     свеж
    -0.06
    POSITIVE LOGITS
    ictor
    0.08
     demons
    0.07
     BufferedWriter
    0.06
     önce
    0.06
     cryptography
    0.06
    olson
    0.06
     Simon
    0.06
    romise
    0.06
     application
    0.06
    Colors
    0.06
    Act Density 0.027%

    No Known Activations