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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extreme
    -0.07
     disin
    -0.07
     estimating
    -0.07
     genome
    -0.06
    Beyond
    -0.06
     strange
    -0.06
    яз
    -0.06
    „
    -0.06
     foresee
    -0.06
     platform
    -0.06
    POSITIVE LOGITS
    /apple
    0.07
     حالی
    0.06
     اجتماع
    0.06
     آلات
    0.06
     nouvelle
    0.06
    _CANCEL
    0.06
    왕
    0.06
     spec
    0.06
     혹
    0.06
    ид
    0.06
    Act Density 0.037%

    No Known Activations