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

    Neuronpedia

    INDEX
    Explanations

    qualities, data, or systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .).
    1.20
     ().
    1.13
     سکے۔
    1.06
    。(
    1.05
     ).
    1.04
     گی۔
    1.00
    ().
    0.96
    )。
    0.95
    ئیں۔
    0.95
    ()).
    0.94
    POSITIVE LOGITS
    ,
    1.61
    —
    1.39
    ,</
    1.39
    ،
    1.32
    --
    1.28
    ,—
    1.23
    ,<
    1.19
    -,
    1.18
     –
    1.17
    ——
    1.17
    Act Density 0.427%

    No Known Activations