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

    Neuronpedia

    INDEX
    Explanations

    studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appreh
    -0.07
     GB
    -0.07
     cyber
    -0.06
    clean
    -0.06
     avatar
    -0.06
     trunk
    -0.06
    �
    -0.06
     runners
    -0.06
    ТО
    -0.06
     PRICE
    -0.06
    POSITIVE LOGITS
    ifications
    0.07
    .
↵↵
    0.06
    _Long
    0.06
    、い
    0.06
    scores
    0.06
     tisk
    0.06
    '>{
    0.06
     vyd
    0.06
     науков
    0.06
    ={"
    0.06
    Act Density 0.027%

    No Known Activations