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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _feed
    -0.07
    celona
    -0.06
     tower
    -0.06
     adapters
    -0.06
     credits
    -0.06
     Fits
    -0.06
     культур
    -0.06
    -sync
    -0.06
     thưởng
    -0.06
    ナー
    -0.06
    POSITIVE LOGITS
    ennifer
    0.07
    صبح
    0.06
     threatened
    0.06
    .''
    0.06
    (big
    0.06
    _bid
    0.06
     sân
    0.06
    _SURFACE
    0.06
     pleasing
    0.06
     yell
    0.06
    Act Density 0.000%

    No Known Activations