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

    Neuronpedia

    INDEX
    Explanations

    specific problems or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    0.46
    士
    0.45
    主要
    0.44
     toho
    0.42
    лейбол
    0.41
    ubei
    0.40
    ęcia
    0.40
     perin
    0.39
    ástico
    0.39
    而
    0.39
    POSITIVE LOGITS
    坟
    0.51
    谕
    0.47
     Кі
    0.44
     Рус
    0.44
     constants
    0.43
     उत्तम
    0.43
     virtues
    0.43
     絵
    0.43
     multer
    0.41
     agendas
    0.41
    Act Density 0.000%

    No Known Activations