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

    Neuronpedia

    INDEX
    Explanations

    classification, numeric, quantitative, categorical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     домаш
    0.95
     Domestic
    0.93
     mainstream
    0.90
     domést
    0.89
    Domestic
    0.87
     domestic
    0.87
     домашних
    0.85
    居家
    0.84
     domác
    0.83
     эксплуатации
    0.82
    POSITIVE LOGITS
     numeric
    1.23
     quantitative
    1.13
     binary
    1.12
     numerical
    1.10
     berupa
    1.09
     quantifiable
    1.06
     tangible
    1.05
     intangible
    1.05
     audio
    1.03
    quantitative
    1.02
    Act Density 0.364%

    No Known Activations