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

    Neuronpedia

    INDEX
    Explanations

    it followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.77
    i
    0.74
    نا
    0.70
    l
    0.70
    n
    0.59
    ir
    0.58
    this
    0.58
    r
    0.57
    m
    0.57
    nia
    0.56
    POSITIVE LOGITS
     inoltre
    0.67
    т
    0.66
    지만
    0.61
     had
    0.61
     are
    0.59
    кий
    0.58
    ة
    0.57
     eléctricos
    0.56
    д
    0.56
     were
    0.55
    Act Density 1.976%

    No Known Activations