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

    Neuronpedia

    INDEX
    Explanations

    The capitalized names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рование
    0.54
    тех
    0.52
     hóa
    0.48
     וא
    0.46
    entation
    0.46
    Из
    0.45
    và
    0.45
     calorimetry
    0.45
     kỹ
    0.45
    ס
    0.45
    POSITIVE LOGITS
     Pirate
    0.54
     Crime
    0.49
     ballad
    0.49
     Channel
    0.48
     Chairman
    0.47
     Voyage
    0.47
     Night
    0.47
     Story
    0.47
     Ring
    0.47
     Weird
    0.47
    Act Density 0.014%

    No Known Activations