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

    Neuronpedia

    INDEX
    Explanations

    NPR copyright and transcripts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    开始
    -0.08
    פשט
    -0.07
     één
    -0.07
     дол
    -0.06
     quarters
    -0.06
    🅛
    -0.06
    土豆
    -0.06
    瞟
    -0.06
     Emacs
    -0.06
     durante
    -0.06
    POSITIVE LOGITS
    iew
    0.08
     constr
    0.07
    iate
    0.07
     closes
    0.07
    owe
    0.07
    Abb
    0.07
    уз
    0.07
    Ao
    0.07
     Rew
    0.07
    誤
    0.07
    Act Density 0.001%

    No Known Activations