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

    Neuronpedia

    INDEX
    Explanations

    currently

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Locker
    -0.07
     clipping
    -0.06
    -animation
    -0.06
     baskets
    -0.06
    VOICE
    -0.06
     authenticated
    -0.06
     tirelessly
    -0.06
    -feedback
    -0.05
     omas
    -0.05
    ories
    -0.05
    POSITIVE LOGITS
    为什么
    0.07
     Almighty
    0.07
     nguy
    0.07
     Rhino
    0.07
     Dee
    0.06
     nimi
    0.06
    ugins
    0.06
    vendor
    0.06
    olvers
    0.06
    ğer
    0.06
    Act Density 0.019%

    No Known Activations