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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ở
    -0.07
     return
    -0.06
     Return
    -0.06
     yayım
    -0.06
     trips
    -0.06
     though
    -0.06
    }))
    -0.06
     mandate
    -0.06
     outrageous
    -0.06
     addresses
    -0.06
    POSITIVE LOGITS
     {[
    0.06
    ční
    0.06
    /////////////////////////////////////////////////////////////////////////////↵
    0.06
    _SLAVE
    0.06
    출장안마
    0.06
     พฤศจ
    0.06
     Dante
    0.06
     ит
    0.06
    */↵↵↵
    0.06
    ITIZE
    0.06
    Act Density 0.000%

    No Known Activations