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

    Neuronpedia

    INDEX
    Explanations

    generate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    فقد
    -0.08
     textual
    -0.07
    多余的
    -0.07
    帏
    -0.07
    monthly
    -0.07
    уча
    -0.07
     bụng
    -0.07
    МИ
    -0.07
     فقد
    -0.07
     mesma
    -0.07
    POSITIVE LOGITS
    暂
    0.07
     navigator
    0.06
     Raleigh
    0.06
     quar
    0.06
    半导
    0.06
    ями
    0.06
     größ
    0.06
    的合作
    0.06
    Arn
    0.06
    OS
    0.06
    Act Density 0.033%

    No Known Activations