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

    Neuronpedia

    INDEX
    Explanations

    goes on forever without repeating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tabular
    0.45
     money
    0.42
    zv
    0.40
     denaro
    0.40
     milliards
    0.40
     dinheiro
    0.39
    每年
    0.39
    currencies
    0.38
    mamm
    0.38
    salary
    0.37
    POSITIVE LOGITS
    继续
    0.54
     продолжа
    0.53
     continua
    0.52
     Rek
    0.51
     继续
    0.49
     continuing
    0.49
     Continuing
    0.49
     Продол
    0.48
     продолжи
    0.48
     folyt
    0.48
    Act Density 0.004%

    No Known Activations