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

    Neuronpedia

    INDEX
    Explanations

    code execution, software usage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NOI
    -0.08
     اعتماد
    -0.08
    adena
    -0.08
    waju
    -0.07
     קש
    -0.07
     принято
    -0.07
     اخ
    -0.07
    pono
    -0.07
     previo
    -0.07
    sero
    -0.07
    POSITIVE LOGITS
     테스트
    0.10
     thử
    0.09
     sliders
    0.09
     ausprobieren
    0.08
    Try
    0.08
     Try
    0.08
    测试
    0.08
     hopefully
    0.08
    点击
    0.08
    ，希望
    0.08
    Act Density 0.008%

    No Known Activations