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

    Neuronpedia

    INDEX
    Explanations

    choose option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrayBox
    0.44
    StarObject
    0.40
    ayy
    0.39
     탄
    0.39
    ्रेन
    0.39
    ূত
    0.39
     매출
    0.39
    icelli
    0.38
    AssetsResponse
    0.38
    탄
    0.38
    POSITIVE LOGITS
     mode
    0.90
     ignore
    0.89
     verbose
    0.89
     Ignore
    0.84
    mode
    0.84
    ignore
    0.84
    オプション
    0.84
     allow
    0.82
    选项
    0.82
     enable
    0.80
    Act Density 0.092%

    No Known Activations