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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َّ
    -0.07
     Lust
    -0.07
    ahi
    -0.07
     già
    -0.07
     ك
    -0.07
    ós
    -0.07
    ológ
    -0.06
    ασίας
    -0.06
     SVC
    -0.06
     ecosystems
    -0.06
    POSITIVE LOGITS
    ota
    0.07
     kles
    0.07
    ,Th
    0.06
    .builder
    0.06
    ---------
    0.06
     lưu
    0.06
    lenme
    0.06
     gears
    0.06
    FromString
    0.06
     -↵
    0.06
    Act Density 0.025%

    No Known Activations