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

    Neuronpedia

    INDEX
    Explanations

    Short abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -to
    -0.08
     imageView
    -0.07
     Rock
    -0.06
    	ip
    -0.06
     assertTrue
    -0.06
    .Intent
    -0.06
    Launcher
    -0.06
    ≦
    -0.06
     worries
    -0.06
    enzyme
    -0.06
    POSITIVE LOGITS
    d
    0.12
    D
    0.11
     td
    0.11
    د
    0.11
    AD
    0.11
    д
    0.11
    ad
    0.10
     Mond
    0.10
    LD
    0.10
    ads
    0.10
    Act Density 1.512%

    No Known Activations