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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ing
    -0.09
    .On
    -0.08
    jant
    -0.08
     Gaussian
    -0.08
    Gaussian
    -0.08
    (clk
    -0.08
    ieli
    -0.07
     sédu
    -0.07
    .Spring
    -0.07
    	Spring
    -0.07
    POSITIVE LOGITS
     inferred
    0.12
     extracted
    0.12
     extraction
    0.11
    .extract
    0.11
    Extract
    0.11
     extracts
    0.11
     extracting
    0.11
     extract
    0.10
     Extract
    0.10
     استخراج
    0.10
    Act Density 0.155%

    No Known Activations