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

    Neuronpedia

    INDEX
    Explanations

    hex color codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ماحول
    0.49
    養
    0.48
    ாதை
    0.44
    Suburb
    0.43
    его
    0.42
    鄯
    0.41
     واحده
    0.41
     காலநிலை
    0.41
    環境
    0.40
     환경
    0.40
    POSITIVE LOGITS
     =>
    0.47
     nh
    0.47
     New
    0.47
    as
    0.46
             
    0.46
    '
    0.46
     (
    0.45
    ल
    0.45
     Word
    0.45
     aks
    0.44
    Act Density 0.031%

    No Known Activations