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

    Neuronpedia

    INDEX
    Explanations

    parentheses, brackets, and curly braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?”
    -2.67
    ’，
    -2.66
    嗞
    -2.66
    ”،
    -2.61
    𖥦
    -2.55
    喼
    -2.50
    Коммента
    -2.48
    )।
    -2.41
    ？”
    -2.33
     berdua
    -2.33
    POSITIVE LOGITS
     MOST
    2.91
    .
    2.73
     —
    2.67
    。
    2.67
    ].
    2.64
    .[
    2.59
    .’
    2.58
     VERY
    2.53
    ."
    2.48
     [(
    2.48
    Act Density 0.004%

    No Known Activations