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

    Neuronpedia

    INDEX
    Explanations

    Russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aé
    -0.08
     Lum
    -0.07
    ampling
    -0.07
     integrate
    -0.07
    Lum
    -0.07
    [p
    -0.07
     luminos
    -0.07
    [][]
    -0.07
     survive
    -0.07
     combination
    -0.07
    POSITIVE LOGITS
    _pt
    0.09
    했던
    0.09
     Lied
    0.09
     küs
    0.08
     пер
    0.08
     צר
    0.08
    0.08
     Occasionally
    0.08
     RESET
    0.08
     cadeira
    0.08
    Act Density 0.009%
    No Known Activations