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

    Neuronpedia

    INDEX
    Explanations

    predicting outcomes and making bets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prevState
    0.44
    randomNumber
    0.44
     remarquable
    0.44
     mamm
    0.43
     theoret
    0.42
    ≙
    0.42
    vrdr
    0.42
    哺乳
    0.41
    慟
    0.41
    体験
    0.41
    POSITIVE LOGITS
    bet
    0.67
     bet
    0.60
     betting
    0.57
     bets
    0.56
    Bet
    0.55
     Bet
    0.54
     Yahoo
    0.53
     picks
    0.51
    priced
    0.51
    Yahoo
    0.51
    Act Density 0.069%

    No Known Activations