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

    Neuronpedia

    INDEX
    Explanations

    data parsing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     servlet
    -0.07
     police
    -0.07
    车
    -0.07
     roar
    -0.07
     спри
    -0.07
     Dropbox
    -0.06
    こんに
    -0.06
     parti
    -0.06
     expedition
    -0.06
     arp
    -0.06
    POSITIVE LOGITS
     ----------------
    0.06
    _Controller
    0.06
    /read
    0.06
    cisi
    0.06
     darüber
    0.06
    _UNSIGNED
    0.05
    لت
    0.05
    าตรฐาน
    0.05
     şar
    0.05
    WORD
    0.05
    Act Density 0.019%

    No Known Activations