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

    Neuronpedia

    INDEX
    Explanations

    programming syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "]="
    0.78
     Vitt
    0.75
    Margaret
    0.75
     __________
    0.74
    ીએ
    0.73
    <unused2117>
    0.73
    0.73
    荪
    0.73
     Pengembangan
    0.72
     _______
    0.72
    POSITIVE LOGITS
    ().
    1.30
    ).
    1.17
     while
    1.13
    $.
    1.12
     ).
    1.11
    。
    1.10
     。
    1.06
    >.
    1.05
     instead
    1.04
    而不是
    1.03
    Act Density 0.233%

    No Known Activations