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

    Neuronpedia

    INDEX
    Explanations

    magnetic fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.08
    :
    0.84
    的
    0.77
     машине
    0.69
    ant
    0.67
    it
    0.64
    [
    0.64
     جمهور
    0.63
    (
    0.63
     traged
    0.61
    POSITIVE LOGITS
    त
    0.78
    ри
    0.72
    AK
    0.63
    کس
    0.62
    Anche
    0.61
    рав
    0.60
    ری
    0.59
    リ
    0.59
    Questo
    0.59
    IAB
    0.59
    Act Density 0.003%

    No Known Activations