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

    Neuronpedia

    INDEX
    Explanations

    writing new episodes of tv shows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laatste
    0.51
     senaste
    0.51
     last
    0.50
     latest
    0.49
     viime
    0.48
     mLast
    0.47
     recent
    0.47
     마지막
    0.46
     ultimi
    0.46
     последние
    0.45
    POSITIVE LOGITS
     нашего
    0.40
    ڏ
    0.40
    WWE
    0.39
    カー
    0.39
    ड़
    0.38
    ProguardFile
    0.38
    『
    0.38
     naše
    0.37
    charger
    0.37
     Overwatch
    0.37
    Act Density 0.004%

    No Known Activations