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

    Neuronpedia

    INDEX
    Explanations

    Cast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    征
    -0.08
    電
    -0.07
     hứng
    -0.07
    -al
    -0.07
    /trans
    -0.07
    小さな
    -0.07
    @update
    -0.07
    .action
    -0.07
    董事
    -0.07
    .failure
    -0.07
    POSITIVE LOGITS
    softmax
    0.07
    iego
    0.07
     def
    0.07
     finest
    0.07
    ⚤
    0.07
    '>↵
    0.06
    ولوجي
    0.06
     Esto
    0.06
    erring
    0.06
     יצירת
    0.06
    Act Density 0.004%

    No Known Activations