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

    Neuronpedia

    INDEX
    Explanations

    **past tense verbs followed by by or as**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ina
    1.41
    ون
    1.20
    ia
    1.19
    eng
    1.17
    >
    1.15
    ări
    1.14
    one
    1.12
    ினும்
    1.11
    i
    1.09
    g
    1.09
    POSITIVE LOGITS
     aback
    1.18
     sacc
    1.13
    是用
    1.13
    ய்ய
    1.12
    ுள்ளார்
    1.12
     fibr
    1.08
    До
    1.06
     жүктөө
    1.05
    ーツ
    1.05
    AMES
    1.05
    Act Density 0.255%

    No Known Activations