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

    Neuronpedia

    INDEX
    Explanations

    transmission and car parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     более
    0.68
     اكثر
    0.66
     יותר
    0.65
     గొప్ప
    0.64
    assapi
    0.62
     lebih
    0.61
     больш
    0.61
     больше
    0.61
    ),"
    0.61
     regio
    0.58
    POSITIVE LOGITS
    х
    0.60
    8
    0.59
    箴
    0.58
    formatted
    0.57
    ข
    0.56
    2
    0.54
    d
    0.54
    5
    0.53
     trabajando
    0.53
    Data
    0.52
    Act Density 0.054%

    No Known Activations