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

    Neuronpedia

    INDEX
    Explanations

    JOIN clause conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ريف
    0.56
    ست
    0.55
    رم
    0.53
    ્રો
    0.53
    рата
    0.53
    је
    0.52
    يك
    0.52
     árvore
    0.52
    لي
    0.51
    Ле
    0.50
    POSITIVE LOGITS
    on
    0.60
    (
    0.57
    EU
    0.50
    4
    0.49
    8
    0.49
    selt
    0.49
    tests
    0.47
    test
    0.46
    AT
    0.45
    EST
    0.45
    Act Density 0.000%

    No Known Activations