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

    Neuronpedia

    INDEX
    Explanations

    responsibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    寇
    -0.07
    mits
    -0.07
    harma
    -0.06
     toutes
    -0.06
     GAP
    -0.06
    anches
    -0.06
    殷
    -0.06
    irement
    -0.06
     envis
    -0.06
     Lum
    -0.06
    POSITIVE LOGITS
    방송
    0.07
     getUsername
    0.07
    /root
    0.07
    شؤ
    0.07
     đăng
    0.07
     twe
    0.06
    👞
    0.06
    Purchase
    0.06
     uptime
    0.06
    太
    0.06
    Act Density 0.092%

    No Known Activations