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

    Neuronpedia

    INDEX
    Explanations

    to + verb to explain purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subtitles
    0.56
     spf
    0.52
     locais
    0.52
     skis
    0.50
     personas
    0.49
     coro
    0.49
     splits
    0.48
     spotlights
    0.48
     els
    0.48
     renders
    0.48
    POSITIVE LOGITS
    し
    0.63
    -
    0.60
    ры
    0.56
    gain
    0.56
    0.56
    1
    0.55
    ก
    0.54
    き
    0.54
    あります
    0.52
    annya
    0.50
    Act Density 0.266%

    No Known Activations