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

    Neuronpedia

    INDEX
    Explanations

    dialogue turns or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ivar
    0.61
    gi
    0.55
    '
    0.52
    thi
    0.52
    is
    0.51
    ij
    0.50
    ces
    0.50
    ca
    0.49
    Се
    0.49
    ki
    0.48
    POSITIVE LOGITS
     attribu
    0.47
     সোনার
    0.41
     সমাপ্ত
    0.41
     rapide
    0.41
     Wonders
    0.41
     सदी
    0.40
     ች
    0.40
    mainframe
    0.40
     Year
    0.39
     Industria
    0.39
    Act Density 0.001%

    No Known Activations