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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -ator"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ecal
    -0.07
     itching
    -0.06
     Olympia
    -0.06
     relocated
    -0.06
     Internal
    -0.06
     internal
    -0.06
     Payments
    -0.06
     Transform
    -0.06
     delegated
    -0.06
     mountain
    -0.06
    POSITIVE LOGITS
    ��
    0.07
     Gaz
    0.07
    一步
    0.07
     để
    0.06
    _LAT
    0.06
    	IN
    0.06
    _ram
    0.06
    (INPUT
    0.06
     _|
    0.06
     "^
    0.06
    Act Density 0.002%

    No Known Activations