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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ctx
    -0.07
     associative
    -0.07
    .build
    -0.07
     Phon
    -0.06
    ビジ
    -0.06
    compose
    -0.06
    쁄
    -0.06
    bool
    -0.06
     conject
    -0.06
    的理解
    -0.06
    POSITIVE LOGITS
    '];?>"
    0.08
     Samar
    0.07
     Dies
    0.07
    ,:)
    0.07
     모든
    0.07
    -LAST
    0.07
    玉石
    0.07
     members
    0.07
     Movies
    0.06
     Comey
    0.06
    Act Density 0.003%

    No Known Activations