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

    Neuronpedia

    INDEX
    Explanations

    .static

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .SE
    -0.08
     разі
    -0.08
    -sh
    -0.07
     puzzles
    -0.07
    .getChannel
    -0.06
     ilgili
    -0.06
     batchSize
    -0.06
    βο
    -0.06
    502
    -0.06
     jedoch
    -0.06
    POSITIVE LOGITS
    薬
    0.07
     lil
    0.06
     projectiles
    0.06
     uranium
    0.06
     默认
    0.06
    iming
    0.06
     सकत
    0.06
     Jay
    0.06
     engagement
    0.06
     ramp
    0.06
    Act Density 0.002%

    No Known Activations