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

    Neuronpedia

    INDEX
    Explanations

    modifying list during iteration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CO
    -0.07
     functions
    -0.07
     MMM
    -0.06
    两会
    -0.06
    pData
    -0.06
    出
    -0.06
    判断
    -0.06
    暇
    -0.06
    生病
    -0.06
     Política
    -0.06
    POSITIVE LOGITS
     Meat
    0.08
     Penny
    0.07
    จอง
    0.07
     ambition
    0.07
    .*,
    0.07
    News
    0.07
     NOAA
    0.07
    הצל
    0.06
     tapi
    0.06
    filer
    0.06
    Act Density 0.036%

    No Known Activations