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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ện
    -0.07
    Being
    -0.07
    下调
    -0.07
    ceived
    -0.07
    传言
    -0.07
    етесь
    -0.06
    butt
    -0.06
    ["_
    -0.06
    letion
    -0.06
    ewn
    -0.06
    POSITIVE LOGITS
     metre
    0.07
    яз
    0.07
     בשלב
    0.07
     vagina
    0.07
    みなさん
    0.07
    	api
    0.07
     особенно
    0.07
    	HX
    0.07
    (ca
    0.07
     api
    0.07
    Act Density 0.001%

    No Known Activations