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

    Neuronpedia

    INDEX
    Explanations

    contextual terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     :");
    0.52
     लाहिड़ी
    0.47
    _:
    0.46
    utscher
    0.45
     :
    0.44
    isati
    0.44
     প্রবাহিত
    0.43
     :#
    0.43
    》（
    0.43
    熔
    0.43
    POSITIVE LOGITS
    한
    0.49
     dismal
    0.48
     solemn
    0.47
     Donnelly
    0.47
     Feynman
    0.47
    भारतीय
    0.46
    চাই
    0.45
    ிர்
    0.43
     meal
    0.43
     problem
    0.43
    Act Density 0.002%

    No Known Activations