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

    Neuronpedia

    INDEX
    Explanations

    commas followed by and or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sondern
    0.99
     theyre
    0.98
     schrift
    0.91
    $.;
    0.90
    ഡി
    0.90
     pretože
    0.89
     $)
    0.88
     fxaa
    0.87
    ய்டா
    0.85
     deoarece
    0.84
    POSITIVE LOGITS
    ,
    1.02
    :
    0.85
     (
    0.84
    —
    0.83
    ...
    0.80
      
    0.79
    --
    0.78
     –
    0.72
    0.70
    -
    0.68
    Act Density 0.199%

    No Known Activations