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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables like x, y, c

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    0.52
    6
    0.52
    5
    0.51
    4
    0.48
    :
    0.48
    7
    0.46
    9
    0.42
    ک
    0.41
    이었
    0.39
    이지만
    0.38
    POSITIVE LOGITS
    0.40
     from
    0.39
     C
    0.34
    <0x8C>
    0.32
     I
    0.31
     K
    0.30
    ia
    0.30
    GoObject
    0.30
     На
    0.30
     politici
    0.30
    Act Density 0.463%

    No Known Activations