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

    Neuronpedia

    INDEX
    Explanations

    quiet followed by a state or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.01
    ’
    0.92
    ।’
    0.66
    ↵↵
    0.65
    ’।
    0.64
    ↵
    0.61
     =
    0.60
     hints
    0.59
     лиц
    0.59
     hid
    0.58
    POSITIVE LOGITS
    약
    0.83
    на
    0.79
    at
    0.78
    B
    0.78
    وم
    0.77
    Third
    0.75
    E
    0.75
    Type
    0.74
    Area
    0.73
    Market
    0.73
    Act Density 0.019%

    No Known Activations