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

    Neuronpedia

    INDEX
    Explanations

    layout attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patham
    0.64
     কর্ম
    0.61
    archiw
    0.61
     челу
    0.60
    expandindo
    0.60
     **,
    0.59
     কীভাবে
    0.58
     attham
    0.58
     pomocí
    0.58
    काशी
    0.57
    POSITIVE LOGITS
     for
    1.01
     be
    1.00
    у
    0.79
    et
    0.76
    هم
    0.74
    um
    0.73
    ă
    0.73
    ન
    0.72
    ب
    0.70
    بة
    0.70
    Act Density 0.001%

    No Known Activations