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

    Neuronpedia

    INDEX
    Explanations

    [placeholder] [instruction]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Asalamualaikum
    0.57
    อะคาเดมี
    0.55
     bhavanti
    0.54
     kvůli
    0.54
     gamanam
    0.51
     Feel
    0.50
     bitOp
    0.50
     allah
    0.50
    ৮
    0.49
    কারণ
    0.49
    POSITIVE LOGITS
    en
    0.50
    mode
    0.48
    CN
    0.47
    uper
    0.45
    ut
    0.44
    نيف
    0.44
    professor
    0.44
    dealer
    0.43
    mor
    0.43
    newspaper
    0.43
    Act Density 0.001%

    No Known Activations