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

    Neuronpedia

    INDEX
    Explanations

    resources and services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ceremonies
    -0.08
    faculty
    -0.06
     RequestOptions
    -0.06
     Artem
    -0.06
    mark
    -0.06
    覚
    -0.06
     Path
    -0.06
     rhet
    -0.06
     Less
    -0.06
     Cookies
    -0.06
    POSITIVE LOGITS
    ňování
    0.07
    transport
    0.07
    ...(
    0.06
     okol
    0.06
    шается
    0.06
    snapshot
    0.06
    availability
    0.06
     afford
    0.06
     talep
    0.06
     přístup
    0.06
    Act Density 0.053%

    No Known Activations