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

    Neuronpedia

    INDEX
    Explanations

    pledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jiangsu
    0.77
     답
    0.74
     întreb
    0.74
     rookie
    0.73
     suspended
    0.72
     carpenter
    0.71
     répondre
    0.71
    બંધ
    0.71
     enumer
    0.70
     Trivia
    0.69
    POSITIVE LOGITS
    ט
    0.97
    什么
    0.84
    на
    0.81
    0.79
    ૄ
    0.77
    σης
    0.75
    <0x80>
    0.75
    oing
    0.75
    و
    0.74
     fanden
    0.73
    Act Density 0.000%

    No Known Activations