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

    Neuronpedia

    INDEX
    Explanations

    invoice and date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িলার
    0.40
    स्पेक्टर
    0.38
     империи
    0.37
     ਦਾ
    0.37
     सैयद
    0.37
    Probit
    0.37
    頫
    0.36
     উপনিবেশ
    0.36
    phasis
    0.36
     ١
    0.36
    POSITIVE LOGITS
     سای
    0.45
    夏天
    0.39
     protection
    0.39
     بای
    0.39
     summer
    0.38
     densidad
    0.37
    衫
    0.37
     Hager
    0.36
     hat
    0.35
     كث
    0.35
    Act Density 0.000%

    No Known Activations