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

    Neuronpedia

    INDEX
    Explanations

    years and ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಉತ್
    0.29
     হজযাত্র
    0.29
    রির
    0.28
     indebtedness
    0.27
    itosan
    0.27
    일부터
    0.27
    WMat
    0.26
    Despatx
    0.26
     ಸಂಧಿ
    0.26
     vacuo
    0.25
    POSITIVE LOGITS
    ,
    0.34
    ),
    0.29
    )
    0.29
     -
    0.28
     /
    0.28
     –
    0.27
    ):
    0.27
     ID
    0.27
    )|
    0.27
    ).
    0.27
    Act Density 0.007%

    No Known Activations