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

    Neuronpedia

    INDEX
    Explanations

    requests for information or generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    但在
    0.53
    かもしれませんが
    0.53
     ولكن
    0.51
     ancak
    0.50
     सभी
    0.50
    但是在
    0.49
     wszyscy
    0.49
     แต่
    0.48
    이지만
    0.47
     لكن
    0.47
    POSITIVE LOGITS
    ä
    0.54
    ing
    0.54
     are
    0.53
     can
    0.51
     to
    0.46
     would
    0.45
    3
    0.45
     will
    0.45
    ene
    0.44
     could
    0.44
    Act Density 0.731%

    No Known Activations