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

    Neuronpedia

    INDEX
    Explanations

    in the hands of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     የተለያዩ
    0.79
    нда
    0.70
    ээр
    0.70
     المثلثيه
    0.69
    Funds
    0.68
    ኋ
    0.67
     راجس
    0.67
    шат
    0.66
    ел
    0.66
     እንቅ
    0.66
    POSITIVE LOGITS
    al
    0.98
    ing
    0.97
    at
    0.94
    ed
    0.92
    4
    0.88
    8
    0.84
     hands
    0.80
     on
    0.79
    ian
    0.79
    3
    0.77
    Act Density 0.001%

    No Known Activations