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

    Neuronpedia

    INDEX
    Explanations

    time spent or taken

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     නැ
    0.67
     borrower
    0.62
     ശക്ത
    0.60
     নদী
    0.60
    ải
    0.59
    aryngeal
    0.59
     μό
    0.59
     உயர்ந்த
    0.58
     onder
    0.58
    tta
    0.58
    POSITIVE LOGITS
    差不多
    0.67
     prohibit
    0.63
    ভাবেই
    0.61
    ⵅ
    0.60
     صبح
    0.59
     চাই
    0.58
     significantly
    0.58
     disproportion
    0.58
     decreasing
    0.57
     போலவே
    0.57
    Act Density 0.112%

    No Known Activations