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

    Neuronpedia

    INDEX
    Explanations

    relatively

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sanit
    -0.07
     saw
    -0.07
     sector
    -0.06
     touch
    -0.06
     drink
    -0.06
     Seen
    -0.06
    igned
    -0.06
     push
    -0.06
     Paulo
    -0.06
    .UR
    -0.06
    POSITIVE LOGITS
     relatively
    0.10
     comparatively
    0.08
    相当
    0.07
    articles
    0.07
    financial
    0.07
     inadvert
    0.07
    allele
    0.07
    čemž
    0.07
    本
    0.07
     \<^
    0.07
    Act Density 0.009%

    No Known Activations