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

    Neuronpedia

    INDEX
    Explanations

    Physics/Polarization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     payout
    -0.06
    '{
    -0.06
    руп
    -0.06
    -cond
    -0.06
    调查
    -0.06
     ()↵
    -0.06
     illustrator
    -0.06
     supposedly
    -0.06
    _PCIE
    -0.06
    ToggleButton
    -0.06
    POSITIVE LOGITS
    .Inv
    0.07
    rpc
    0.07
     compel
    0.07
     sæ
    0.07
     colossal
    0.06
     Discrim
    0.06
    Sample
    0.06
     Hd
    0.06
     Required
    0.06
     divor
    0.06
    Act Density 0.029%

    No Known Activations