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

    Neuronpedia

    INDEX
    Explanations

    `__name__`

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᗢ
    -0.07
    ѷ
    -0.07
    已经在
    -0.07
    破产
    -0.07
    新
    -0.07
    קיימים
    -0.06
    蔬菜
    -0.06
    تنظيم
    -0.06
    revision
    -0.06
     hybrid
    -0.06
    POSITIVE LOGITS
     INCLUDE
    0.08
     ROUND
    0.07
     EDGE
    0.07
    ERVICE
    0.07
     cha
    0.07
    ersed
    0.07
    atron
    0.07
    Globals
    0.07
    夺
    0.06
    HONE
    0.06
    Act Density 0.004%

    No Known Activations