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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vér
    0.44
    ლებ
    0.44
     modalCard
    0.41
    ➀
    0.39
    ków
    0.38
     коюм
    0.38
    ór
    0.37
    œurs
    0.37
     ось
    0.37
    ávají
    0.36
    POSITIVE LOGITS
     unofficial
    0.43
     cao
    0.40
     half
    0.39
     perimeter
    0.39
     Official
    0.37
     apex
    0.36
     official
    0.36
    Official
    0.36
     *
    0.36
    )));
    0.36
    Act Density 0.076%

    No Known Activations