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

    Neuronpedia

    INDEX
    Explanations

    measurable attributes and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ک
    0.48
    לא
    0.48
    し
    0.43
    لا
    0.43
    نا
    0.39
    بال
    0.37
    ます
    0.36
    ニ
    0.36
     ۔
    0.35
    א
    0.35
    POSITIVE LOGITS
    at
    0.47
    am
    0.47
    ak
    0.47
    on
    0.44
    i
    0.44
     trustee
    0.41
    el
    0.40
    ig
    0.39
    and
    0.39
     Ryanair
    0.38
    Act Density 1.832%

    No Known Activations