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

    Neuronpedia

    INDEX
    Explanations

    spatial coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.85
    Math
    0.80
    Down
    0.78
    ج
    0.77
    션을
    0.74
    goog
    0.73
    Sonic
    0.73
    Ke
    0.73
    Change
    0.72
    Zhang
    0.71
    POSITIVE LOGITS
     tqdm
    0.83
     automobiles
    0.81
    resse
    0.77
     ವಿಧಾನಸಭಾ
    0.75
    🎄
    0.75
     airplanes
    0.73
    🪵
    0.73
    。",
    0.72
     эксплуа
    0.72
     sbParams
    0.71
    Act Density 0.001%

    No Known Activations