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

    Neuronpedia

    INDEX
    Explanations

    code, software, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DAYS
    -0.07
     whiskey
    -0.07
    354
    -0.07
     Mormons
    -0.07
     Fresno
    -0.06
    quina
    -0.06
     Bottle
    -0.06
     Orioles
    -0.06
    	explicit
    -0.06
    .bmp
    -0.06
    POSITIVE LOGITS
     inner
    0.07
    -navigation
    0.06
     enjoys
    0.06
    лож
    0.06
     ettir
    0.06
    셔
    0.06
    다는
    0.06
    EEP
    0.06
     prin
    0.06
    MediaType
    0.06
    Act Density 0.035%

    No Known Activations