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

    Neuronpedia

    INDEX
    Explanations

    reasons, justifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mort
    -0.07
    links
    -0.07
    刀
    -0.07
     Recipe
    -0.07
    579
    -0.06
    rt
    -0.06
    ався
    -0.06
     diary
    -0.06
     náklady
    -0.06
    感情
    -0.06
    POSITIVE LOGITS
     куль
    0.07
    ">{
    0.06
     пунк
    0.06
    _binding
    0.06
    mpeg
    0.06
    \Message
    0.06
     fis
    0.06
    IRC
    0.06
     after
    0.06
    Field
    0.06
    Act Density 0.121%

    No Known Activations