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

    Neuronpedia

    INDEX
    Explanations

    Size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roker
    -0.08
     �
    -0.06
    ेवल
    -0.06
    уп
    -0.06
    ladığı
    -0.06
    лений
    -0.06
     sang
    -0.06
    ädchen
    -0.06
    .preferences
    -0.06
    (""))
    -0.06
    POSITIVE LOGITS
     settlers
    0.07
     buoy
    0.07
     Hebrew
    0.07
     $('.
    0.07
     procure
    0.06
     barang
    0.06
    ."""
    0.06
     stanice
    0.06
     Dublin
    0.06
     rallies
    0.06
    Act Density 0.004%

    No Known Activations