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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    解
    -0.07
     sabe
    -0.07
     Hear
    -0.07
    -env
    -0.07
     Cord
    -0.07
     British
    -0.07
     cops
    -0.06
     possible
    -0.06
    	gr
    -0.06
     itinerary
    -0.06
    POSITIVE LOGITS
    generic
    0.06
     mínimo
    0.06
    Inspect
    0.06
    έα
    0.06
     mpl
    0.06
     proprio
    0.06
    Sales
    0.06
     λ
    0.06
    _REQUIRE
    0.06
    澤
    0.06
    Act Density 0.071%

    No Known Activations