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

    Neuronpedia

    INDEX
    Explanations

    under and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    1.69
    на
    1.52
    о
    1.32
    јединачна
    1.27
    ോ
    1.25
    ية
    1.16
     postérieures
    1.16
    و
    1.16
    ста
    1.13
    ル
    1.13
    POSITIVE LOGITS
    neath
    1.29
    at
    1.27
    under
    1.15
    '
    1.13
     (
    1.11
     under
    1.11
     on
    1.10
    \
    1.05
    ab
    1.04
    .
    1.00
    Act Density 0.047%

    No Known Activations