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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    艺术
    -0.09
     Calder
    -0.08
    akar
    -0.08
     careers
    -0.08
     surprise
    -0.08
     frontières
    -0.08
    军
    -0.08
     collage
    -0.08
     ejaculation
    -0.07
     कला
    -0.07
    POSITIVE LOGITS
     downhill
    0.10
     uphill
    0.10
    坡
    0.10
     gravitational
    0.10
     incline
    0.10
     upright
    0.10
     sunlight
    0.09
     Incl
    0.09
     inclin
    0.09
    gravity
    0.09
    Act Density 0.010%

    No Known Activations