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

    Neuronpedia

    INDEX
    Explanations

    ]["

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🤞
    -0.08
    xaf
    -0.07
    (APP
    -0.07
    ALES
    -0.07
    (nx
    -0.07
    箨
    -0.07
    trag
    -0.07
    很多人都
    -0.06
    MW
    -0.06
     ''){↵
    -0.06
    POSITIVE LOGITS
     racing
    0.07
    检查
    0.07
     생
    0.07
    但对于
    0.07
     pthread
    0.07
     Stick
    0.06
     ст
    0.06
    马
    0.06
    至于
    0.06
    Images
    0.06
    Act Density 0.002%

    No Known Activations