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

    Neuronpedia

    INDEX
    Explanations

    past tense auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    2.16
    Ν
    1.97
    ously
    1.91
    ，
    1.87
    ੰ
    1.84
     tę
    1.84
    А
    1.77
    ון
    1.75
     majd
    1.73
     crouching
    1.72
    POSITIVE LOGITS
    s
    3.47
     volna
    2.58
    ن
    2.50
    س
    2.45
     autrefois
    2.42
    ের
    2.39
    ों
    2.33
    ات
    2.30
    ین
    2.27
     ANC
    2.23
    Act Density 0.766%

    No Known Activations