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

    Neuronpedia

    INDEX
    Explanations

    player position changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Зап
    -0.07
     Заг
    -0.06
    .enter
    -0.06
     deniz
    -0.06
     walnut
    -0.06
     Savage
    -0.05
     Razor
    -0.05
     connectors
    -0.05
     Mage
    -0.05
    Equal
    -0.05
    POSITIVE LOGITS
     Grand
    0.08
     nei
    0.07
     utiliser
    0.07
     Vers
    0.07
     الأمر
    0.07
    .less
    0.06
    Next
    0.06
     giảm
    0.06
    .Millisecond
    0.06
     Differences
    0.06
    Act Density 0.015%

    No Known Activations