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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .↵↵↵↵↵↵
    -0.07
     умовах
    -0.06
    Bur
    -0.06
    *K
    -0.06
    \">\
    -0.06
    krét
    -0.06
     福
    -0.06
     qs
    -0.06
    のに
    -0.06
     дек
    -0.06
    POSITIVE LOGITS
    Responses
    0.07
     clap
    0.07
     امتی
    0.07
    一个
    0.06
    ザー
    0.06
    loyment
    0.06
    ilians
    0.06
     ray
    0.06
    itr
    0.06
     edilen
    0.06
    Act Density 0.000%

    No Known Activations