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

    Neuronpedia

    INDEX
    Explanations

    normalize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сли
    -0.07
    (d
    -0.06
    	q
    -0.06
    Franc
    -0.06
    우리
    -0.06
    ===========
    -0.06
    spacing
    -0.06
     ELSE
    -0.06
     在线
    -0.06
    IsValid
    -0.06
    POSITIVE LOGITS
     gore
    0.07
     Sadly
    0.07
     sadly
    0.07
    _nb
    0.06
     Couch
    0.06
    ляет
    0.06
    odata
    0.06
     Mouse
    0.06
     cread
    0.06
     ülk
    0.06
    Act Density 0.023%

    No Known Activations