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

    Neuronpedia

    INDEX
    Explanations

    Consumer Financial Protection Bureau

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৬
    1.76
    ৮
    1.61
    是因为
    1.55
    ৭
    1.53
    是个
    1.47
    した
    1.45
    ited
    1.43
    लिये
    1.41
    ভাবে
    1.40
    に着
    1.36
    POSITIVE LOGITS
    ান
    1.67
     moléculas
    1.66
     iż
    1.63
    ׁ
    1.61
     codons
    1.59
    ar
    1.58
     ordeal
    1.54
     dì
    1.52
    на
    1.51
    ખ
    1.51
    Act Density 0.000%

    No Known Activations