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

    Neuronpedia

    INDEX
    Explanations

    general / specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ABET
    0.54
    REAM
    0.52
    SCHRAMM
    0.52
    rivation
    0.51
    pyrid
    0.51
    ISTR
    0.49
    computation
    0.49
    ធី
    0.48
    ಿನಲ್ಲಿ
    0.47
    TON
    0.47
    POSITIVE LOGITS
     Général
    0.52
    ється
    0.50
     Germ
    0.45
    是一
    0.43
     realtà
    0.42
     Bats
    0.41
     Bast
    0.41
    দ্বিত
    0.41
     জেনারেল
    0.40
     General
    0.40
    Act Density 0.002%

    No Known Activations