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

    Neuronpedia

    INDEX
    Explanations

    customizable alerts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    द्धाल
    0.56
    geoType
    0.53
     zichzelf
    0.48
    notifications
    0.48
     Illustrator
    0.48
    ตัวเอง
    0.48
     Hewitt
    0.48
     ArrayRef
    0.48
     LocalDateTime
    0.47
     अधिसू
    0.47
    POSITIVE LOGITS
    ள்ள
    0.49
     resume
    0.42
    cape
    0.42
     ப
    0.41
     desktop
    0.40
    t
    0.40
     to
    0.39
     coral
    0.39
    ...
    0.39
     boot
    0.39
    Act Density 0.001%

    No Known Activations