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

    Neuronpedia

    INDEX
    Explanations

    Tic-Tac-Toe

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    삽
    0.72
    阆
    0.70
     ክፍ
    0.70
     шла
    0.70
     Elle
    0.66
     عطا
    0.66
     Dense
    0.66
    Dense
    0.66
     fundación
    0.64
     sier
    0.63
    POSITIVE LOGITS
    tac
    0.71
     Tac
    0.71
    놓
    0.67
    Tac
    0.67
    ჟ
    0.67
     tac
    0.66
    TAK
    0.62
    笺
    0.61
    уд
    0.61
     toc
    0.60
    Act Density 0.004%

    No Known Activations