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

    Neuronpedia

    INDEX
    Explanations

    sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     genus
    -0.07
     conclusion
    -0.06
     Longitude
    -0.06
    Full
    -0.06
     AUTHOR
    -0.06
     damping
    -0.06
     compañ
    -0.06
    ecedor
    -0.06
    enate
    -0.06
    letion
    -0.06
    POSITIVE LOGITS
     signage
    0.09
    牌
    0.07
     demographics
    0.07
     ~~
    0.07
    kı
    0.07
     scenery
    0.07
    ‐‐
    0.06
    ﺮ
    0.06
    PUT
    0.06
    BarItem
    0.06
    Act Density 0.014%

    No Known Activations