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

    Neuronpedia

    INDEX
    Explanations

    llll

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    逸
    -0.07
    媒
    -0.07
    (IO
    -0.06
    ANGED
    -0.06
     FIR
    -0.06
     ens
    -0.06
     matriz
    -0.06
    Oops
    -0.06
    алом
    -0.06
    _por
    -0.06
    POSITIVE LOGITS
    Une
    0.07
     Aff
    0.07
    §ظ
    0.06
    _PHONE
    0.06
    监听页面
    0.06
    并不
    0.06
    _DL
    0.06
     smiles
    0.06
    uttle
    0.06
    	scene
    0.06
    Act Density 0.000%

    No Known Activations