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

    Neuronpedia

    INDEX
    Explanations

    pride oneself on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     président
    0.76
     or
    0.69
     minister
    0.62
     presidente
    0.62
     Presidente
    0.62
     president
    0.61
    Window
    0.61
     l
    0.61
    м
    0.59
     mairie
    0.59
    POSITIVE LOGITS
    ურთი
    0.68
    𝘵
    0.67
     сово
    0.64
    сово
    0.63
    bets
    0.63
    ubers
    0.62
     operatives
    0.61
    kernels
    0.60
    uties
    0.59
    ровка
    0.59
    Act Density 0.002%

    No Known Activations