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

    Neuronpedia

    INDEX
    Explanations

    including lists or details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     некоторое
    0.44
    2
    0.43
     &&
    0.42
     Women
    0.42
    農業
    0.41
     nešto
    0.41
     অপ
    0.41
    Women
    0.40
    sleep
    0.40
    1
    0.40
    POSITIVE LOGITS
    ఎల్
    0.46
    altung
    0.44
    UEN
    0.41
     punctures
    0.40
    יא
    0.38
    venida
    0.37
    ইডি
    0.37
     tund
    0.37
     gluon
    0.37
     invis
    0.36
    Act Density 0.008%

    No Known Activations