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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ewn
    -0.08
    956
    -0.07
     Gloria
    -0.06
    718
    -0.06
     Verg
    -0.06
    _regression
    -0.06
    agrams
    -0.06
     exported
    -0.06
    LPARAM
    -0.06
    \Field
    -0.06
    POSITIVE LOGITS
     ан
    0.08
     haciendo
    0.07
     hanno
    0.07
     impe
    0.07
     بن
    0.07
     Norfolk
    0.06
    -serving
    0.06
    	UN
    0.06
     GIVEN
    0.06
     way
    0.06
    Act Density 0.010%

    No Known Activations