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

    Neuronpedia

    INDEX
    Explanations

    Ur words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    heids
    0.45
    လုံး
    0.41
    ló
    0.40
     Everglades
    0.40
    lance
    0.39
    sx
    0.38
    度が
    0.38
    ying
    0.38
     Provision
    0.38
     Wrestle
    0.38
    POSITIVE LOGITS
     UR
    0.75
     Ur
    0.66
     ур
    0.63
     Url
    0.62
     url
    0.61
    Ur
    0.61
     ur
    0.60
     uri
    0.60
    url
    0.57
     URL
    0.57
    Act Density 0.021%

    No Known Activations