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

    Neuronpedia

    INDEX
    Explanations

    Scientific documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ساده
    -0.08
    dir
    -0.07
    /top
    -0.06
    根本
    -0.06
    (region
    -0.06
    IZER
    -0.06
    	ptr
    -0.06
    ibName
    -0.06
    ,str
    -0.06
     billig
    -0.06
    POSITIVE LOGITS
     edad
    0.07
     пись
    0.06
    _take
    0.06
    ainers
    0.06
    .instant
    0.06
    gradation
    0.06
    _TEM
    0.06
    .Nombre
    0.06
     SZ
    0.06
     наг
    0.06
    Act Density 0.037%

    No Known Activations