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

    Neuronpedia

    INDEX
    Explanations

    breakdown, explanation, details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ​​
    0.80
     Dent
    0.78
     Warm
    0.77
     Testament
    0.74
     Herbal
    0.72
     Stand
    0.72
     bào
    0.72
     Spark
    0.71
     True
    0.70
     Aham
    0.70
    POSITIVE LOGITS
    approach
    0.74
    Approach
    0.73
    ↵
    0.72
    uidas
    0.69
    例外
    0.69
    Références
    0.68
    驅
    0.68
    또한
    0.67
    सुद्धा
    0.66
    ymology
    0.66
    Act Density 0.144%

    No Known Activations