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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /io
    -0.08
     магнит
    -0.08
    /vector
    -0.08
     gripe
    -0.08
     Tele
    -0.08
     inalám
    -0.08
     состоянии
    -0.08
     喜
    -0.08
     magnitude
    -0.08
     firefox
    -0.08
    POSITIVE LOGITS
     ખર્ચ
    0.10
     खर्च
    0.10
    成本
    0.09
     tailored
    0.09
     entrepreneurs
    0.09
    Cost
    0.09
     비용
    0.09
     entrepreneur
    0.08
    集中
    0.08
    安心
    0.08
    Act Density 0.048%

    No Known Activations