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

    Neuronpedia

    INDEX
    Explanations

    explaining things that work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poderá
    0.49
     använder
    0.47
     має
    0.45
     může
    0.45
    언
    0.43
     reçu
    0.43
    薜
    0.43
     μπορεί
    0.43
     обладает
    0.42
     reçoit
    0.42
    POSITIVE LOGITS
     and
    0.55
     a
    0.51
     the
    0.50
    c
    0.46
     M
    0.44
    the
    0.43
     Vector
    0.43
    and
    0.43
    l
    0.42
     N
    0.42
    Act Density 0.000%

    No Known Activations