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

    Neuronpedia

    INDEX
    Explanations

    specific thread or antenna

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saws
    0.97
     classiques
    0.93
     replacements
    0.89
    inationals
    0.87
    PCs
    0.86
    regulars
    0.85
     supplémentaires
    0.85
    ameras
    0.84
    rossovers
    0.83
    ార్లు
    0.83
    POSITIVE LOGITS
     selected
    1.03
    当該
    1.01
     chosen
    0.97
     jeweil
    0.94
     particular
    0.83
     betreff
    0.83
     jeweiligen
    0.82
     gesamte
    0.82
     adott
    0.77
     해당
    0.77
    Act Density 0.651%

    No Known Activations