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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     specifics
    -0.07
    总算
    -0.07
    כניס
    -0.06
    秦皇
    -0.06
    市委常委
    -0.06
    _Element
    -0.06
    -selector
    -0.06
    大卫
    -0.06
    TouchListener
    -0.06
    Structure
    -0.06
    POSITIVE LOGITS
    佚
    0.08
    借助
    0.07
    FE
    0.07
    感叹
    0.07
     Nazis
    0.07
    ＄
    0.07
    ание
    0.07
     Ger
    0.06
    きちんと
    0.06
    GRAM
    0.06
    Act Density 0.276%

    No Known Activations