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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _outputs
    -0.08
     pickup
    -0.07
     gần
    -0.07
    oy
    -0.07
    成熟的
    -0.07
     Russian
    -0.07
     Carolina
    -0.06
    .builder
    -0.06
     dic
    -0.06
    熟
    -0.06
    POSITIVE LOGITS
    舭
    0.08
    راتيج
    0.07
    㙍
    0.07
    𝔞
    0.07
    筘
    0.07
    _EXPECT
    0.07
    PageRoute
    0.07
    lanması
    0.07
    뙇
    0.07
    //----------------
    0.07
    Act Density 0.048%

    No Known Activations