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

    Neuronpedia

    INDEX
    Explanations

    examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    าตรฐาน
    -0.07
    �
    -0.07
    ेद
    -0.07
    iad
    -0.07
    .Pro
    -0.06
    рид
    -0.06
    द
    -0.06
    sei
    -0.06
    _QU
    -0.06
     sanitary
    -0.06
    POSITIVE LOGITS
     Gym
    0.07
     smashed
    0.07
     improvements
    0.07
     opens
    0.07
    ={
    0.06
    nap
    0.06
     introducing
    0.06
     suppression
    0.06
    ">{
    0.06
     exercise
    0.06
    Act Density 0.002%

    No Known Activations