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

    Neuronpedia

    INDEX
    Explanations

    success and achievement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ct
    0.85
     dogma
    0.83
     ostensibly
    0.80
     statusCode
    0.79
     glared
    0.78
     lapse
    0.78
     Proceeds
    0.75
    }'
    0.75
     Pollution
    0.74
     decorator
    0.74
    POSITIVE LOGITS
    ли
    0.99
     jooks
    0.94
     trajetória
    0.88
    ل
    0.80
     lavoro
    0.80
    imee
    0.79
    ა
    0.78
     compartió
    0.78
    каў
    0.75
     carreira
    0.75
    Act Density 0.313%

    No Known Activations