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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (proxy
    -0.08
    zek
    -0.08
     situ
    -0.08
     mak
    -0.07
    烙
    -0.07
    mis
    -0.07
    .My
    -0.07
    שוב
    -0.07
    _GAP
    -0.07
    一幅
    -0.07
    POSITIVE LOGITS
     ViewController
    0.08
     TOP
    0.07
    懑
    0.07
     seasonal
    0.07
    おすす
    0.07
     arsenal
    0.07
    Subviews
    0.06
    DataContract
    0.06
    ョン
    0.06
     layoffs
    0.06
    Act Density 0.004%

    No Known Activations