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

    Neuronpedia

    INDEX
    Explanations

    conditions as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ambra
    1.12
    ullahi
    1.09
    distanceArray
    1.06
    樱
    1.04
    ække
    1.03
    orderLine
    1.02
    umboldt
    1.02
    عبير
    1.02
    uleiro
    1.02
    kernel
    1.01
    POSITIVE LOGITS
    .).
    1.00
    .)
    0.98
     club
    0.91
    .);
    0.88
    .),
    0.88
     whom
    0.87
    ).
    0.86
    ’
    0.86
    .​​
    0.86
    .
    0.86
    Act Density 0.005%

    No Known Activations