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

    Neuronpedia

    INDEX
    Explanations

    code or URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Graph
    -0.07
     Deutsch
    -0.07
    uru
    -0.07
    sen
    -0.06
    .hour
    -0.06
     Reed
    -0.06
     Disp
    -0.06
    .First
    -0.06
    dfunding
    -0.06
    coal
    -0.06
    POSITIVE LOGITS
     funct
    0.08
    �
    0.07
    must
    0.06
    centage
    0.06
    ?:
    0.06
     considers
    0.06
     hodnot
    0.06
    extField
    0.06
     customers
    0.06
    	output
    0.06
    Act Density 0.000%

    No Known Activations