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

    Neuronpedia

    INDEX
    Explanations

    tic-tac-toe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shielded
    0.41
     Ávila
    0.38
     shrubs
    0.37
    عهد
    0.37
    佛教
    0.37
     duplicated
    0.36
    भि
    0.36
    ပြု
    0.36
     liik
    0.36
    illery
    0.35
    POSITIVE LOGITS
     Tic
    0.86
     tic
    0.80
    Tic
    0.78
    tic
    0.70
     nought
    0.60
     TIC
    0.59
    TacToe
    0.55
    TIC
    0.54
     X
    0.52
    XO
    0.49
    Act Density 0.013%

    No Known Activations