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

    Neuronpedia

    INDEX
    Explanations

    specified or differing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     огромное
    0.91
     부분이
    0.88
     многое
    0.87
     부분
    0.86
     всегда
    0.85
     zorgt
    0.84
     кое
    0.83
     luôn
    0.83
    פי
    0.82
    有些
    0.82
    POSITIVE LOGITS
     specified
    1.26
     or
    1.21
     whom
    1.05
     alebo
    1.05
     किंवा
    1.03
     differing
    1.01
     または
    1.00
     eller
    0.98
    或
    0.97
    または
    0.96
    Act Density 0.713%

    No Known Activations