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

    Neuronpedia

    INDEX
    Explanations

    legal terms and pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stabbing
    1.00
    átil
    0.94
     mirip
    0.94
     नींबू
    0.93
    ibly
    0.90
     illusions
    0.88
    rawdę
    0.87
     dung
    0.86
    iaal
    0.86
     tens
    0.84
    POSITIVE LOGITS
     aul
    0.86
     შესახებ
    0.84
    mig
    0.84
    los
    0.81
     Weiter
    0.80
     breakouts
    0.78
    OU
    0.77
     Bereiche
    0.75
    CE
    0.73
    மைகள்
    0.72
    Act Density 0.037%

    No Known Activations