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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Check
    -0.09
    Dit
    -0.08
     regal
    -0.08
    Responsive
    -0.07
     crise
    -0.07
     peanut
    -0.07
    Directories
    -0.07
    DEBUG
    -0.07
     Chapters
    -0.07
    ультура
    -0.07
    POSITIVE LOGITS
     Reven
    0.09
     born
    0.08
     sparks
    0.08
     запуск
    0.08
     સાધ
    0.08
    	login
    0.08
     Sparks
    0.08
     меч
    0.07
     cube
    0.07
     burning
    0.07
    Act Density 0.000%

    No Known Activations