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

    Neuronpedia

    INDEX
    Explanations

    声东击西

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asena
    0.61
     subsum
    0.51
     фарма
    0.47
    i
    0.46
    ദേ
    0.44
    MERS
    0.43
     asserts
    0.43
     Ад
    0.43
    Devil
    0.43
    nante
    0.43
    POSITIVE LOGITS
     এলাকায়
    0.43
     Ramón
    0.43
     letteratura
    0.43
    目に
    0.42
     trochu
    0.42
     একদিন
    0.42
    ိပ်
    0.42
     littérature
    0.42
    startTime
    0.41
    敗
    0.41
    Act Density 0.002%

    No Known Activations