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

    Neuronpedia

    INDEX
    Explanations

    trade regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idle
    -0.06
    apo
    -0.06
     actu
    -0.06
     crane
    -0.06
    Ê
    -0.06
    eg
    -0.06
    avana
    -0.06
    在
    -0.06
    Bro
    -0.06
    740
    -0.06
    POSITIVE LOGITS
     αλλά
    0.07
     paranormal
    0.07
     insurgency
    0.07
    =node
    0.07
     hiểm
    0.06
    (encoded
    0.06
     sélection
    0.06
    .parseColor
    0.06
    	↵
    0.06
     строитель
    0.06
    Act Density 0.017%

    No Known Activations