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

    Neuronpedia

    INDEX
    Explanations

    story/news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skul
    -0.08
     greater
    -0.08
    ‘y
    -0.07
     incomparable
    -0.07
    來
    -0.07
     czego
    -0.07
    than
    -0.07
    阳市
    -0.07
    ORS
    -0.07
     해야
    -0.07
    POSITIVE LOGITS
     अचानक
    0.11
     verloren
    0.11
     integrity
    0.10
     നഷ്ട
    0.10
     abruptly
    0.10
     loses
    0.09
    .destroy
    0.09
     Destroy
    0.09
     verlieren
    0.09
     потер
    0.09
    Act Density 0.303%

    No Known Activations