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

    Neuronpedia

    INDEX
    Explanations

    ad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    list
    -0.08
     deng
    -0.07
    manual
    -0.07
     Grammarly
    -0.07
     Nazis
    -0.07
     pir
    -0.07
    dram
    -0.07
    difference
    -0.07
    poster
    -0.07
    grep
    -0.07
    POSITIVE LOGITS
     Applicable
    0.09
     accompanied
    0.08
     substitutions
    0.08
     applied
    0.08
     Applic
    0.08
     disclaimer
    0.08
     applicable
    0.07
    Applic
    0.07
     accompanying
    0.07
     Applied
    0.07
    Act Density 0.037%

    No Known Activations