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

    Neuronpedia

    INDEX
    Explanations

    white house

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ate
    0.75
    ane
    0.75
    that
    0.73
    Fig
    0.72
    one
    0.71
     P
    0.70
     CBD
    0.68
     White
    0.67
     T
    0.67
     that
    0.67
    POSITIVE LOGITS
    ।
    1.42
    एस
    1.38
    。
    1.23
    ۔
    1.08
    ف
    1.00
    。</
    0.99
    。【
    0.96
    एम
    0.95
    کم
    0.92
    ی
    0.92
    Act Density 0.000%

    No Known Activations