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

    Neuronpedia

    INDEX
    Explanations

    past tense statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.53
    u
    0.50
    tc
    0.41
    на
    0.40
    тся
    0.39
     amphibians
    0.39
    apadam
    0.39
     compos
    0.38
    ulates
    0.38
     οποία
    0.38
    POSITIVE LOGITS
    OU
    0.46
    Wert
    0.45
    *
    0.44
    ET
    0.44
    ع
    0.43
    Quan
    0.40
    EL
    0.40
     dennoch
    0.39
    /
    0.39
    ے
    0.39
    Act Density 0.103%

    No Known Activations