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

    Neuronpedia

    INDEX
    Explanations

    mirrors, reflecting light

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .subscription
    -0.09
    科研
    -0.08
    纪律
    -0.08
    _RELEASE
    -0.08
    .seq
    -0.08
     disciplined
    -0.08
    .disconnect
    -0.07
     orderly
    -0.07
    .qu
    -0.07
     taua
    -0.07
    POSITIVE LOGITS
     Furniture
    0.09
     Wallpapers
    0.08
     hostess
    0.08
     furniture
    0.08
    clamation
    0.08
     жақ
    0.08
     работ
    0.08
     меньше
    0.08
     ampl
    0.08
     CSS
    0.08
    Act Density 0.011%

    No Known Activations