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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ṛ
    0.36
    ০০
    0.36
    isVideo
    0.34
     শরণার্থীরা
    0.34
     বিরোধী
    0.34
    טא
    0.33
     пытается
    0.33
    Externe
    0.33
    Snap
    0.32
     পরিবহন
    0.32
    POSITIVE LOGITS
    orgetown
    0.50
     Kansas
    0.45
     west
    0.44
     Springfield
    0.43
     Washington
    0.43
     Sonoma
    0.43
     West
    0.42
    anigans
    0.40
     Worcester
    0.39
     न्यू
    0.39
    Act Density 0.001%

    No Known Activations