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

    Neuronpedia

    INDEX
    Explanations

    FDA removed warning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     よろしく
    0.42
    🫡
    0.42
    🩷
    0.42
     Measurements
    0.40
     округу
    0.40
    ⸙
    0.39
    details
    0.39
    InputBorder
    0.39
    Visible
    0.39
     要素
    0.39
    POSITIVE LOGITS
     late
    0.43
     midnight
    0.40
     لی
    0.40
    ეთი
    0.40
    ron
    0.38
     canned
    0.38
     hiver
    0.38
     foolish
    0.38
    وصل
    0.38
     einer
    0.37
    Act Density 0.001%

    No Known Activations