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

    Neuronpedia

    INDEX
    Explanations

    categorized by feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    因为它
    1.01
    它的
    1.01
     two
    0.98
    Its
    0.87
     its
    0.84
    把它
    0.84
     everybody
    0.84
     două
    0.83
     två
    0.83
     Its
    0.82
    POSITIVE LOGITS
     varying
    2.02
     either
    1.91
    varying
    1.83
     либо
    1.71
    それぞれ
    1.70
    either
    1.68
    各自
    1.67
     respective
    1.65
     Either
    1.65
     jeweiligen
    1.65
    Act Density 0.759%

    No Known Activations