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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     半
    -0.06
    닉
    -0.06
     Inhal
    -0.06
    .Platform
    -0.06
    ╝
    -0.06
    طه
    -0.06
     NotImplemented
    -0.06
     уров
    -0.06
    뮤
    -0.06
     dieta
    -0.06
    POSITIVE LOGITS
    .scss
    0.07
     mechanic
    0.06
     })↵
    0.06
     weiber
    0.06
    而
    0.06
     Richie
    0.06
    ندی
    0.06
    alling
    0.06
    oracle
    0.06
     اصلی
    0.06
    Act Density 0.052%

    No Known Activations