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

    Neuronpedia

    INDEX
    Explanations

    raising exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bounding
    0.39
    TakePhoto
    0.38
     माधव
    0.37
     dominating
    0.37
    neſs
    0.37
    痢
    0.37
    த்தோ
    0.37
     vire
    0.36
     kr
    0.36
     NSR
    0.36
    POSITIVE LOGITS
     from
    0.54
    Exc
    0.49
    FROM
    0.48
    from
    0.47
     FROM
    0.47
     від
    0.46
     fromi
    0.45
    으로부터
    0.44
     therefrom
    0.43
    From
    0.42
    Act Density 0.002%

    No Known Activations