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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ENABLE
    -0.07
    &E
    -0.06
    Ping
    -0.06
    078
    -0.06
    -enh
    -0.06
    (pdf
    -0.06
    �
    -0.06
     Essentials
    -0.06
    {{{
    -0.06
     SendMessage
    -0.06
    POSITIVE LOGITS
    ัวเอง
    0.07
    něm
    0.07
     주문
    0.06
    .Dense
    0.06
     jewel
    0.06
     elemental
    0.06
    Systems
    0.06
     APPLE
    0.06
    циональ
    0.06
    /port
    0.06
    Act Density 0.041%

    No Known Activations