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

    Neuronpedia

    INDEX
    Explanations

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     زیب
    -0.08
     李
    -0.06
    ван
    -0.06
    (gen
    -0.06
    рати
    -0.06
     Nurs
    -0.06
     sn
    -0.06
    ITIES
    -0.06
     nurs
    -0.06
    Tank
    -0.06
    POSITIVE LOGITS
    诉
    0.07
    とは
    0.07
     </
    0.06
    <footer
    0.06
     cite
    0.06
     param
    0.06
    \system
    0.06
     skating
    0.06
    法
    0.06
    ثل
    0.06
    Act Density 0.000%

    No Known Activations