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

    Neuronpedia

    INDEX
    Explanations

    official names followed by of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     、,
    0.43
    羵
    0.40
    }^\
    0.38
    さんは
    0.37
    .$,
    0.37
    اا
    0.36
    ।,
    0.36
    Bundes
    0.36
     atti
    0.35
     सिलसिले
    0.35
    POSITIVE LOGITS
     of
    1.24
     ഓഫ്
    0.90
     ऑफ
    0.85
    of
    0.84
     của
    0.73
     của
    0.70
     Of
    0.67
     של
    0.67
     오브
    0.67
     ఆఫ్
    0.67
    Act Density 0.040%

    No Known Activations