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

    Neuronpedia

    INDEX
    Explanations

    Names, relationships and lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Services
    -0.08
     וח
    -0.08
    FileSize
    -0.07
    sville
    -0.07
    _receipt
    -0.07
    _certificate
    -0.07
    .Green
    -0.07
    扮演游戏
    -0.06
    >M
    -0.06
     כמובן
    -0.06
    POSITIVE LOGITS
     producción
    0.08
     alpha
    0.07
    تعا
    0.07
    cpp
    0.07
     fields
    0.07
     BITS
    0.07
    ala
    0.06
    rames
    0.06
    .rule
    0.06
    팥
    0.06
    Act Density 0.029%

    No Known Activations