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

    Neuronpedia

    INDEX
    Explanations

    a -dimensional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мор
    -0.07
     Toilet
    -0.07
     nir
    -0.07
     Rosie
    -0.07
     Missile
    -0.06
     LE
    -0.06
    ｉ
    -0.06
     CLI
    -0.06
     catch
    -0.06
    .Queue
    -0.06
    POSITIVE LOGITS
     stakes
    0.07
     beams
    0.07
    умент
    0.06
    odynam
    0.06
     registering
    0.06
     welded
    0.06
    .curve
    0.06
    äge
    0.06
     brokers
    0.06
     simplified
    0.06
    Act Density 0.084%

    No Known Activations