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

    Neuronpedia

    INDEX
    Explanations

    <title> tag content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :<
    0.39
     könne
    0.38
     saute
    0.35
     interrogated
    0.35
    :“
    0.34
     maga
    0.34
     NONE
    0.33
     induced
    0.32
     inherited
    0.32
     seas
    0.32
    POSITIVE LOGITS
     Untitled
    0.54
    Untitled
    0.54
    MyApp
    0.50
    제목
    0.49
     My
    0.48
    My
    0.48
    untitled
    0.48
     my
    0.46
     untitled
    0.46
    setWindowTitle
    0.46
    Act Density 0.006%

    No Known Activations