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

    Neuronpedia

    INDEX
    Explanations

    URLs and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     authoritarian
    0.41
     bahagia
    0.40
     verwend
    0.40
     tenga
    0.39
     verdes
    0.39
     dictum
    0.39
     zwei
    0.39
     قصير
    0.38
    بعض
    0.38
    好きな
    0.37
    POSITIVE LOGITS
     trong
    0.44
    ต่างๆ
    0.42
     throughout
    0.39
    细节
    0.38
     ώστε
    0.38
     μέσα
    0.37
     during
    0.37
    数据
    0.37
    Trong
    0.37
    以及
    0.36
    Act Density 2.814%

    No Known Activations