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

    Neuronpedia

    INDEX
    Explanations

    then verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fallback
    0.62
     поло
    0.55
    wax
    0.53
    звичай
    0.51
    ведения
    0.49
    0.49
     День
    0.49
    cliente
    0.49
     Каза
    0.49
     Вы
    0.48
    POSITIVE LOGITS
    ত
    0.62
    ד
    0.61
    ，“
    0.61
     lockdowns
    0.61
    ，
    0.61
    ,?
    0.59
    ッド
    0.58
    ,''
    0.58
    对于
    0.56
    ，「
    0.56
    Act Density 0.000%

    No Known Activations