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

    Neuronpedia

    INDEX
    Explanations

    time after or from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     successivamente
    0.72
     разных
    0.70
     ढाई
    0.67
     বাইরে
    0.66
    two
    0.65
    ומים
    0.65
     значительно
    0.64
     YouTube
    0.64
     Zwe
    0.64
     различных
    0.64
    POSITIVE LOGITS
    初始
    0.67
    で
    0.67
    目安
    0.61
    目標
    0.61
    เริ่ม
    0.60
    Singolare
    0.59
    正常
    0.58
    目标
    0.57
     onset
    0.57
    始める
    0.57
    Act Density 0.092%

    No Known Activations