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

    Neuronpedia

    INDEX
    Explanations

    can read, build, recognize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ദൈവ
    0.34
    綪
    0.32
    archiw
    0.31
    矵
    0.31
    喡
    0.31
    靗
    0.31
     suure
    0.30
    iverso
    0.29
    ࢯ
    0.29
     positifs
    0.29
    POSITIVE LOGITS
    0.40
    ↵↵
    0.36
    ↵
    0.34
    。
    0.29
     "
    0.28
    ]
    0.27
    <strong>
    0.27
     G
    0.26
     '
    0.26
     Car
    0.26
    Act Density 0.000%

    No Known Activations