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

    Neuronpedia

    INDEX
    Explanations

    paper feeding mechanism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -opt
    -0.07
    :↵↵↵↵
    -0.07
     вкус
    -0.07
     Cement
    -0.07
     denotes
    -0.07
    .detect
    -0.07
     ITEM
    -0.07
     נית
    -0.07
     Sass
    -0.07
    Nice
    -0.06
    POSITIVE LOGITS
    万美元
    0.07
    落到
    0.06
    潮
    0.06
     parameter
    0.06
    -au
    0.06
    .Real
    0.06
    ئ
    0.06
    傳
    0.06
    ব
    0.06
    国内
    0.06
    Act Density 0.024%

    No Known Activations