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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    measure
    -0.06
     сервер
    -0.06
     Ibrahim
    -0.06
    سنگ
    -0.06
    hom
    -0.06
    lion
    -0.06
     Gaz
    -0.06
     ilgi
    -0.06
    .mit
    -0.06
    .tele
    -0.06
    POSITIVE LOGITS
     periodically
    0.07
    .bool
    0.06
    틱
    0.06
     jub
    0.06
     Organic
    0.06
     Jamaica
    0.06
     ubyt
    0.06
     chaque
    0.06
     continuously
    0.06
     cis
    0.06
    Act Density 0.013%

    No Known Activations