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

    Neuronpedia

    INDEX
    Explanations

    GPT-4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    de
    0.93
     opsi
    0.89
     inilah
    0.89
     aneurysm
    0.89
     tumbuhan
    0.86
    ann
    0.85
    ”),
    0.85
    ubehör
    0.85
     histó
    0.84
     comunità
    0.84
    POSITIVE LOGITS
     있는
    0.98
    Το
    0.88
    Да
    0.85
    Ла
    0.85
    Ди
    0.84
    Этот
    0.84
    Dtos
    0.84
    자기
    0.84
    телни
    0.82
    лет
    0.81
    Act Density 0.015%

    No Known Activations