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

    Neuronpedia

    INDEX
    Explanations

    adverbs of frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    時間で
    -1.13
    これは
    -1.10
     이미
    -1.05
    議院
    -0.94
    Lenin
    -0.91
    Lindo
    -0.90
    もあって
    -0.86
    んで
    -0.86
    Hermoso
    -0.85
    ポイントは
    -0.84
    POSITIVE LOGITS
     daily
    1.03
    tilizer
    1.00
     people
    1.00
     regarded
    0.98
    以外の
    0.97
     when
    0.97
     monthly
    0.96
    lemény
    0.94
     gets
    0.93
     mismas
    0.93
    Act Density 0.084%

    No Known Activations