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

    Neuronpedia

    INDEX
    Explanations

    language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    জিও
    0.69
    ses
    0.64
    शै
    0.63
    सेट
    0.62
    জু
    0.60
     Els
    0.58
     புல
    0.57
    ลา
    0.57
    యో
    0.57
    getSaveLocation
    0.57
    POSITIVE LOGITS
     রাইফ
    0.70
    基
    0.69
    薙
    0.65
    rici
    0.65
    푚
    0.64
    rice
    0.63
    ेशनल
    0.63
    真人
    0.63
    chamber
    0.63
    मैट
    0.62
    Act Density 0.167%

    No Known Activations