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

    Neuronpedia

    INDEX
    Explanations

    here are some resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이나
    0.45
     ან
    0.43
     или
    0.42
    호
    0.41
    โ
    0.41
    Overall
    0.41
    overall
    0.39
    详情
    0.39
    の新
    0.38
    或者
    0.38
    POSITIVE LOGITS
     ejemplos
    0.46
     handy
    0.46
     jaoks
    0.44
     excelentes
    0.44
     utiles
    0.43
     partur
    0.42
     savons
    0.41
     useful
    0.41
     उपयोगी
    0.41
     contenant
    0.41
    Act Density 0.622%

    No Known Activations