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

    Neuronpedia

    INDEX
    Explanations

    asking you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wonderful
    1.45
     awesome
    1.38
    素晴らしい
    1.34
     excellent
    1.31
     fantastic
    1.28
     amazing
    1.27
    素敵
    1.26
    wonderful
    1.23
     marvelous
    1.21
     lovely
    1.16
    POSITIVE LOGITS
    ◞
    0.43
     პირადი
    0.37
    entions
    0.36
    шаем
    0.36
    ከል
    0.35
     kiş
    0.35
    ༩
    0.35
    ┘
    0.34
    һы
    0.33
     physiologically
    0.33
    Act Density 0.145%

    No Known Activations