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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    通信
    -0.07
    nowledge
    -0.07
    Interrupt
    -0.06
    кові
    -0.06
     Cinema
    -0.06
     Interrupt
    -0.06
    ternet
    -0.06
    евые
    -0.06
     说
    -0.06
    Enterprise
    -0.06
    POSITIVE LOGITS
    .Work
    0.06
     нен
    0.06
     çı
    0.06
     demo
    0.06
     wore
    0.06
     vě
    0.06
     Extraction
    0.06
     scaleY
    0.06
    (sim
    0.06
     MAX
    0.06
    Act Density 0.228%

    No Known Activations