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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ensed
    -0.08
     ş
    -0.07
    JE
    -0.07
     Tart
    -0.07
    _excel
    -0.07
    春节
    -0.07
     строки
    -0.07
    oz
    -0.07
     фут
    -0.07
    (AL
    -0.07
    POSITIVE LOGITS
     individual
    0.07
     __
    0.07
    _operation
    0.07
    __*/
    0.07
    emu
    0.07
     partners
    0.07
    sam
    0.07
    Utility
    0.06
     earning
    0.06
    //(
    0.06
    Act Density 0.009%

    No Known Activations