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

    Neuronpedia

    INDEX
    Explanations

    accountability for actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ના
    0.45
    ные
    0.45
    ला
    0.44
    0.41
    लेकिन
    0.40
     Cál
    0.40
     မ
    0.40
     तभी
    0.40
    त्मक
    0.39
     Philippines
    0.38
    POSITIVE LOGITS
    i
    0.63
    0
    0.61
    י
    0.61
    x
    0.59
    n
    0.59
    w
    0.57
    ed
    0.54
    ats
    0.54
    2
    0.52
     for
    0.52
    Act Density 0.021%

    No Known Activations