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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Angle
    -0.07
    ylan
    -0.07
    aval
    -0.07
    OSE
    -0.07
     Glass
    -0.06
     dřev
    -0.06
     helped
    -0.06
     totalement
    -0.06
    votes
    -0.06
    国家
    -0.06
    POSITIVE LOGITS
     ©
    0.07
     เส
    0.07
     bron
    0.06
     DNS
    0.06
     inspiring
    0.06
    '),
    0.06
     pups
    0.06
    Mask
    0.06
    .Drawable
    0.06
     nuanced
    0.06
    Act Density 0.005%

    No Known Activations