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

    Neuronpedia

    INDEX
    Explanations

    produce, * , nap, under

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ীরের
    0.50
     lapisan
    0.47
     buurt
    0.47
    ूक
    0.46
    ार्किक
    0.44
    SnackBar
    0.44
    ień
    0.43
    ക്കളുടെ
    0.43
     व्यावहारिक
    0.43
     sm
    0.43
    POSITIVE LOGITS
    يش
    0.52
    [
    0.45
    د
    0.44
    فير
    0.43
    مي
    0.43
    ကြ
    0.42
    2
    0.42
    ACI
    0.41
    raron
    0.41
    ه
    0.41
    Act Density 0.002%

    No Known Activations