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

    Neuronpedia

    INDEX
    Explanations

    your advice and needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ομά
    0.47
     τὸν
    0.46
     διάρκ
    0.46
     نویس
    0.46
     паліты
    0.46
    擄
    0.46
     війни
    0.45
    ับสน
    0.45
    軲
    0.45
     offens
    0.44
    POSITIVE LOGITS
    у
    0.51
    g
    0.49
    ể
    0.46
     Veuillez
    0.46
    í
    0.45
    ين
    0.45
    ية
    0.45
    i
    0.45
    필
    0.42
    ام
    0.42
    Act Density 0.001%

    No Known Activations