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

    Neuronpedia

    INDEX
    Explanations

    array and string slicing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    giene
    0.53
    numerical
    0.52
     ज्यामुळे
    0.47
    houses
    0.47
    ivitis
    0.47
    ową
    0.45
    Tangent
    0.45
    ning
    0.44
    tang
    0.44
     කරන
    0.44
    POSITIVE LOGITS
    ح
    0.60
     ي
    0.57
     képes
    0.54
     koncert
    0.52
     ע
    0.52
    𝙩
    0.52
    未
    0.52
    蒉
    0.52
    镟
    0.52
     യാത്ര
    0.51
    Act Density 0.000%

    No Known Activations