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
    民心
    -0.07
    pdo
    -0.07
    ㈳
    -0.07
     Coupe
    -0.07
    מוע
    -0.06
     carving
    -0.06
     alot
    -0.06
    ael
    -0.06
    私服游戏
    -0.06
     Boy
    -0.06
    POSITIVE LOGITS
    Defs
    0.08
    `()
    0.07
    訴
    0.07
    لاحظ
    0.07
    (inv
    0.07
    ...";↵
    0.07
    `.
    0.07
    (""),
    0.07
    .getParent
    0.07
    )";↵↵
    0.07
    Act Density 0.030%

    No Known Activations