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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prod
    -0.06
    favorite
    -0.06
    Learn
    -0.06
    girl
    -0.06
     Repository
    -0.06
    ド
    -0.06
    (trim
    -0.06
    ague
    -0.06
    #ga
    -0.06
    arem
    -0.06
    POSITIVE LOGITS
     inflatable
    0.07
     Patricia
    0.06
     Clarence
    0.06
     Bs
    0.06
    "w
    0.06
    385
    0.06
     deactivated
    0.06
     Confirm
    0.06
     bona
    0.06
     tangible
    0.06
    Act Density 0.017%

    No Known Activations