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

    Neuronpedia

    INDEX
    Explanations

    honour and majesty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     other
    -1.07
    ategor
    -0.97
    iten
    -0.96
     Codable
    -0.94
    ums
    -0.93
     иногда
    -0.90
     some
    -0.89
    bottomRight
    -0.89
     vertes
    -0.89
     indisponible
    -0.88
    POSITIVE LOGITS
     ?????
    0.88
    러한
    0.83
     ഗ
    0.80
     dieną
    0.79
     simpl
    0.79
     لهذه
    0.78
    bram
    0.77
    migiano
    0.77
    J
    0.76
     Lastly
    0.75
    Act Density 0.028%

    No Known Activations