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

    Neuronpedia

    INDEX
    Explanations

    technique

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pus
    -0.08
    ,C
    -0.07
    ,P
    -0.07
    Player
    -0.07
    ,W
    -0.06
    萨
    -0.06
     kles
    -0.06
     donor
    -0.06
    ड
    -0.06
     рост
    -0.06
    POSITIVE LOGITS
    :disable
    0.07
     خارجی
    0.06
    대행
    0.06
     resultList
    0.06
    //
↵
↵
    0.06
    mnt
    0.06
    gement
    0.05
     Tin
    0.05
     eb
    0.05
    учас
    0.05
    Act Density 0.010%

    No Known Activations