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

    Neuronpedia

    INDEX
    Explanations

    interpolation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taller
    -0.07
    σσ
    -0.07
    UBLISH
    -0.07
    -sex
    -0.06
     fierc
    -0.06
    -backend
    -0.06
    _fb
    -0.06
     "<?
    -0.06
    /{
    -0.06
    -season
    -0.06
    POSITIVE LOGITS
     glide
    0.08
    polate
    0.07
    ерим
    0.07
     interpolated
    0.07
    ,...↵
    0.07
    ..↵
    0.06
     unusually
    0.06
     apologies
    0.06
    pora
    0.06
    ば
    0.06
    Act Density 0.005%

    No Known Activations