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

    Neuronpedia

    INDEX
    Explanations

    really

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adir
    -0.08
    ,get
    -0.07
    Viet
    -0.07
    垕
    -0.07
     Quaternion
    -0.07
    oldown
    -0.06
     eject
    -0.06
    太原
    -0.06
    ⌡
    -0.06
    ᕑ
    -0.06
    POSITIVE LOGITS
    makers
    0.09
     role
    0.08
    ✑
    0.07
    .jd
    0.07
     sharp
    0.07
    代表性
    0.07
     speaker
    0.06
     purported
    0.06
    (program
    0.06
     largely
    0.06
    Act Density 0.018%

    No Known Activations