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

    Neuronpedia

    INDEX
    Explanations

    such + descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sổ
    1.30
    బంధ
    1.19
    PECT
    1.18
    ৯
    1.16
    ि
    1.15
    лення
    1.12
     এ
    1.10
     crops
    1.07
    ೋಜನ
    1.07
    वता
    1.07
    POSITIVE LOGITS
    ا
    2.53
    い
    1.69
    ς
    1.66
    ы
    1.59
    ya
    1.59
    y
    1.58
    yani
    1.56
    le
    1.55
    mber
    1.53
    mberg
    1.52
    Act Density 0.073%

    No Known Activations