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

    Neuronpedia

    INDEX
    Explanations

    I am

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    數量
    0.45
     அறிகுற
    0.45
    aparikkh
    0.45
    زمانہ
    0.44
     सिस्टम
    0.43
    umumkan
    0.43
    RIG
    0.43
    ОО
    0.42
    announced
    0.42
    सार
    0.42
    POSITIVE LOGITS
     or
    0.51
     widowed
    0.47
     flights
    0.46
     gowns
    0.46
     dreamy
    0.45
     সম্পাদিত
    0.45
     augmenting
    0.45
     during
    0.44
     বা
    0.44
     when
    0.43
    Act Density 0.004%

    No Known Activations