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

    Neuronpedia

    INDEX
    Explanations

    referral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amphib
    -0.09
     траг
    -0.08
     साँ
    -0.08
    (can
    -0.08
    Focusable
    -0.08
     illusion
    -0.08
    Interpret
    -0.08
    Trajectory
    -0.08
     bł
    -0.08
    rovers
    -0.08
    POSITIVE LOGITS
     incentiv
    0.14
     incentives
    0.13
     incentivar
    0.11
     Incent
    0.11
    奖励
    0.10
    友
    0.10
    邀请
    0.10
     referral
    0.09
     rewarding
    0.09
     incent
    0.09
    Act Density 0.011%

    No Known Activations