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

    Neuronpedia

    INDEX
    Explanations

    estimators, time, purchase, agents, location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    它
    0.52
     rum
    0.50
    血
    0.50
    mesh
    0.48
    本
    0.48
     Rum
    0.47
    用
    0.46
     colored
    0.46
    一
    0.46
    歌
    0.46
    POSITIVE LOGITS
    vät
    0.54
    ｴ
    0.50
     ivvu
    0.49
    ႆ
    0.49
     ultimo
    0.48
     bhavanti
    0.48
     działalności
    0.48
     kautta
    0.47
    IDADE
    0.47
     vadanti
    0.47
    Act Density 0.000%

    No Known Activations