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

    Neuronpedia

    INDEX
    Explanations

    -linked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пред
    -0.07
    TMP
    -0.07
     materially
    -0.07
    	attr
    -0.07
     css
    -0.06
    heets
    -0.06
    argv
    -0.06
    books
    -0.06
     restored
    -0.06
    .env
    -0.06
    POSITIVE LOGITS
    眼部
    0.08
    ика
    0.07
    caf
    0.07
    つまり
    0.07
    Dog
    0.07
    .DropDown
    0.07
    蟑
    0.07
    塥
    0.06
    鹾
    0.06
    可以把
    0.06
    Act Density 0.002%

    No Known Activations