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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .readFile
    -0.07
    ег
    -0.06
     reservoir
    -0.06
    iot
    -0.06
     edged
    -0.06
    .clicked
    -0.06
    丘
    -0.06
     bằng
    -0.06
    .Try
    -0.06
    вор
    -0.06
    POSITIVE LOGITS
    cej
    0.07
     paired
    0.06
     ddl
    0.06
    Should
    0.06
    _sel
    0.06
    Ownership
    0.06
     Concat
    0.06
    rollment
    0.06
     Thousand
    0.06
    .jpeg
    0.06
    Act Density 0.002%

    No Known Activations