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
    +".
    -0.07
     Hassan
    -0.06
    提高
    -0.06
     않는
    -0.06
     migrations
    -0.06
    ::-
    -0.06
    ;">
    -0.06
     PLL
    -0.06
     temsil
    -0.06
     Zhang
    -0.06
    POSITIVE LOGITS
    .insert
    0.06
    ندگی
    0.06
    	reply
    0.06
     setEmail
    0.06
    効
    0.06
    (point
    0.06
    ايت
    0.06
     inputValue
    0.06
    [jj
    0.06
    _board
    0.06
    Act Density 0.000%

    No Known Activations