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

    Neuronpedia

    INDEX
    Explanations

    code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surfaced
    -0.07
     engel
    -0.07
     Hoffman
    -0.06
     دان
    -0.06
     Dup
    -0.06
     twig
    -0.06
    	model
    -0.06
     HomePage
    -0.06
    ‐
    -0.06
     emphasized
    -0.06
    POSITIVE LOGITS
    .engine
    0.07
     Watkins
    0.07
    earable
    0.07
     aller
    0.06
    Conditional
    0.06
     مك
    0.06
    сий
    0.06
    ysts
    0.06
    Review
    0.06
    .openConnection
    0.06
    Act Density 0.001%

    No Known Activations