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

    Neuronpedia

    INDEX
    Explanations

    numeric and time ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bern
    0.58
     metaphor
    0.55
     뜻
    0.54
     Len
    0.54
     Stras
    0.53
     Serum
    0.51
    所在的
    0.51
     En
    0.51
     Teil
    0.50
     nbsp
    0.50
    POSITIVE LOGITS
    –
    1.95
    到
    1.85
    ～
    1.82
     έως
    1.82
     إلى
    1.79
    〜
    1.74
     až
    1.73
    至
    1.73
    -$
    1.69
     đến
    1.66
    Act Density 0.643%

    No Known Activations