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

    Neuronpedia

    INDEX
    Explanations

    user stories about tracking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.46
     片
    0.42
    ↵↵↵
    0.41
    ﹍
    0.41
    ↵↵↵↵
    0.39
     Sind
    0.39
     пропор
    0.39
    ↵↵↵↵↵↵
    0.38
    0.38
    piece
    0.38
    POSITIVE LOGITS
    ড়ের
    0.42
    يير
    0.38
    ዣ
    0.38
    ড়ের
    0.37
    ვით
    0.37
    щика
    0.37
     där
    0.36
     rundt
    0.34
    왔
    0.34
    섰
    0.34
    Act Density 0.001%

    No Known Activations