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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     capsules
    -0.07
     rost
    -0.07
    olders
    -0.06
    lica
    -0.06
     Spi
    -0.06
    öst
    -0.06
     precise
    -0.06
    ==============
    -0.06
    unkt
    -0.06
    .OK
    -0.06
    POSITIVE LOGITS
     Hunger
    0.09
     mailing
    0.07
    ''↵
    0.07
     спіль
    0.07
    ."'
    0.07
    AES
    0.06
     Dangerous
    0.06
     satin
    0.06
     Recomm
    0.06
    _deriv
    0.06
    Act Density 0.004%

    No Known Activations