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

    Neuronpedia

    INDEX
    Explanations

    source of X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لي
    0.91
    يك
    0.89
    ра
    0.79
    も
    0.78
    اري
    0.77
    تي
    0.77
    е
    0.77
    يني
    0.76
    يده
    0.75
    櫒
    0.74
    POSITIVE LOGITS
    of
    1.13
     Sources
    1.00
     sources
    0.93
    a
    0.93
    f
    0.92
     of
    0.89
     źród
    0.86
    ]
    0.86
     source
    0.83
     WHO
    0.83
    Act Density 0.055%

    No Known Activations