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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    戽
    -0.08
     Gor
    -0.07
     E
    -0.07
    滚
    -0.07
    唔
    -0.06
     $('#
    -0.06
    者
    -0.06
    ɽ
    -0.06
     bone
    -0.06
     Wheel
    -0.06
    POSITIVE LOGITS
    计入
    0.08
     objected
    0.07
    multip
    0.07
     outliers
    0.07
    agenta
    0.07
     Bashar
    0.07
    医用
    0.07
    fra
    0.07
    _within
    0.07
    Licensed
    0.07
    Act Density 0.402%

    No Known Activations