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

    Neuronpedia

    INDEX
    Explanations

    multilingual or diverse character sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aromatic
    0.47
    ключа
    0.43
     fratern
    0.42
     monastic
    0.41
     happiest
    0.41
     anna
    0.41
     entour
    0.41
     Lúc
    0.40
     rubric
    0.40
     polys
    0.39
    POSITIVE LOGITS
    動き
    0.46
     京都
    0.46
     जम्मू
    0.45
    睥
    0.44
     »,
    0.44
    াফ
    0.44
    Lf
    0.43
    amburger
    0.43
    »:
    0.43
    δί
    0.43
    Act Density 0.001%

    No Known Activations