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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :return
    -0.06
    остей
    -0.06
     Learned
    -0.06
    :green
    -0.06
     specs
    -0.06
     caregiver
    -0.06
    	object
    -0.06
    /setup
    -0.06
     superb
    -0.06
     Reward
    -0.06
    POSITIVE LOGITS
     pl
    0.07
     Kır
    0.07
    _ot
    0.07
    YPRE
    0.07
     Pl
    0.07
    .Ag
    0.06
     Este
    0.06
     Phạm
    0.06
    =.
    0.06
     уров
    0.06
    Act Density 0.003%

    No Known Activations