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

    Neuronpedia

    INDEX
    Explanations

    not a substitute or guarantee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     padrão
    0.70
     convencional
    0.69
     conventional
    0.68
     standard
    0.65
     conspicuous
    0.65
     estándar
    0.62
    Standard
    0.61
     superfluous
    0.61
     promptly
    0.59
     convenc
    0.58
    POSITIVE LOGITS
     wszystkich
    0.62
     반드시
    0.60
     necessarily
    0.59
    necessarily
    0.57
    ڏ
    0.55
    ૪
    0.55
     всех
    0.54
     beiden
    0.54
     všetky
    0.53
     كامل
    0.52
    Act Density 0.379%

    No Known Activations