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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    νά
    -0.09
     alter
    -0.09
    MMMM
    -0.08
     Vaughan
    -0.08
    .vip
    -0.08
    ologue
    -0.08
     alters
    -0.08
    vod
    -0.08
     Xana
    -0.08
    ША
    -0.08
    POSITIVE LOGITS
    236
    0.12
    449
    0.09
    history
    0.08
    645
    0.08
    übers
    0.08
    828
    0.07
    sqrt
    0.07
    √
    0.07
     öğr
    0.07
    121
    0.07
    Act Density 0.002%

    No Known Activations