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

    Neuronpedia

    INDEX
    Explanations

    semantic memory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verb
    0.40
     Listing
    0.39
     currently
    0.39
     Gabriel
    0.38
     siehe
    0.38
     rhinestone
    0.38
     Palmer
    0.37
     Travis
    0.37
     Leistungen
    0.37
     listings
    0.36
    POSITIVE LOGITS
    իմ
    0.43
    েলে
    0.41
    പ്പെട്ട്
    0.41
    âns
    0.40
    HCO
    0.38
    Origins
    0.37
    齡
    0.37
    攪
    0.36
     良
    0.36
    𝕄
    0.36
    Act Density 0.000%

    No Known Activations