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

    Neuronpedia

    INDEX
    Explanations

    argumentative texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (symbol
    -0.07
     Pep
    -0.07
    QDebug
    -0.07
    atic
    -0.06
     deport
    -0.06
     Gdk
    -0.06
    勇
    -0.06
    ########################################################################
    -0.06
     Mk
    -0.06
     Carolyn
    -0.06
    POSITIVE LOGITS
    _wheel
    0.07
     نشر
    0.07
    orphism
    0.06
    それは
    0.06
     çerçev
    0.06
     ignoring
    0.06
    ->{
    0.06
    حدث
    0.06
    .rect
    0.06
    :create
    0.06
    Act Density 0.260%

    No Known Activations