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

    Neuronpedia

    INDEX
    Explanations

    Software dialects and versions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     गुणव
    -0.09
     quiere
    -0.09
    .GET
    -0.09
    经营
    -0.08
    .pending
    -0.08
    .Pending
    -0.08
     tangible
    -0.08
     наполн
    -0.08
     sobren
    -0.08
     искусства
    -0.08
    POSITIVE LOGITS
     dialect
    0.09
    Recogn
    0.08
    andard
    0.08
     Recogn
    0.08
    型号
    0.08
     специф
    0.08
    recogn
    0.08
     cyclone
    0.08
    iphone
    0.08
    accur
    0.07
    Act Density 0.020%

    No Known Activations