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

    Neuronpedia

    INDEX
    Explanations

    mathematical/scientific terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Owned
    -0.06
    women
    -0.06
     hai
    -0.06
    šov
    -0.06
    member
    -0.06
    computer
    -0.06
     coined
    -0.06
     +(
    -0.06
    *f
    -0.06
    だ
    -0.06
    POSITIVE LOGITS
    ubectl
    0.07
    ullan
    0.07
     chăm
    0.06
    .ResponseWriter
    0.06
    (conv
    0.06
     baff
    0.06
    .Cells
    0.06
     PPC
    0.06
    .SubElement
    0.06
    TextNode
    0.06
    Act Density 0.066%

    No Known Activations