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

    Neuronpedia

    INDEX
    Explanations

    code/math notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compliment
    -0.06
    Profit
    -0.06
     insulting
    -0.06
    leet
    -0.06
    ency
    -0.06
    쉬
    -0.06
    �어
    -0.06
     sağlan
    -0.06
     поход
    -0.06
    anten
    -0.06
    POSITIVE LOGITS
    .listdir
    0.07
     core
    0.06
     سنگ
    0.06
    :bg
    0.06
    (CG
    0.06
     errmsg
    0.06
    ↵        
↵
    0.06
    頭
    0.06
    ेबस
    0.06
     полож
    0.06
    Act Density 0.015%

    No Known Activations