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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     زی
    -0.07
    无码
    -0.07
    nam
    -0.06
     california
    -0.06
    YPD
    -0.06
     edited
    -0.06
     swing
    -0.06
     např
    -0.06
     slender
    -0.06
     faut
    -0.06
    POSITIVE LOGITS
       ↵↵
    0.06
    .gc
    0.06
    }/>↵
    0.06
     ￥
    0.06
    填
    0.06
     attainment
    0.06
    laws
    0.06
    ↵    ↵    ↵
    0.06
    �试
    0.06
     bin
    0.06
    Act Density 0.000%

    No Known Activations