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

    Neuronpedia

    INDEX
    Explanations

    phrases following specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    弄
    0.42
    לא
    0.41
    Lycodon
    0.39
    能
    0.39
    حافظ
    0.39
    eqref
    0.38
    不出
    0.38
     שלא
    0.38
    inflate
    0.38
    絶対
    0.38
    POSITIVE LOGITS
    ethe
    0.45
     several
    0.41
    ęp
    0.40
     tors
    0.40
     classmates
    0.40
     اسرائی
    0.40
    entiti
    0.39
     Algunos
    0.39
     lignes
    0.39
     |
    0.39
    Act Density 0.005%

    No Known Activations