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

    Neuronpedia

    INDEX
    Explanations

    host earnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    عی
    0.41
    ORUS
    0.40
     কর্মকর্ত
    0.39
    传染
    0.39
     investigator
    0.39
    უცი
    0.39
     collation
    0.39
    羣
    0.38
     TEXAS
    0.38
     intoxicating
    0.38
    POSITIVE LOGITS
    view
    0.49
    cta
    0.46
    Read
    0.45
     read
    0.42
     Read
    0.42
     meminta
    0.41
     Lire
    0.41
     odmah
    0.41
     Biographie
    0.40
     mengaku
    0.40
    Act Density 0.000%

    No Known Activations