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

    Neuronpedia

    INDEX
    Explanations

    code member access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thế
    0.33
     تربيع
    0.32
     کي
    0.31
     kttt
    0.31
     ശിഷ്യ
    0.31
    lsulfanyl
    0.30
     Compd
    0.30
    frameN
    0.30
    ྥ
    0.30
     いっ
    0.30
    POSITIVE LOGITS
    .
    0.38
    ::
    0.30
    -
    0.25
    _
    0.25
    \
    0.24
    :
    0.24
    ,
    0.23
    ..
    0.23
    /
    0.23
    <0xC2>
    0.23
    Act Density 0.655%

    No Known Activations