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

    Neuronpedia

    INDEX
    Explanations

    engineer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     responsibilities
    -0.08
     odpowied
    -0.07
     wrist
    -0.07
    しょ
    -0.06
    (at
    -0.06
     dul
    -0.06
    ули
    -0.06
    parameters
    -0.06
     butto
    -0.06
     залеж
    -0.06
    POSITIVE LOGITS
     Hans
    0.06
    Yu
    0.06
     kob
    0.06
    .country
    0.06
    haled
    0.06
     bury
    0.06
     Ge
    0.06
     Shen
    0.06
     kn
    0.06
     mü
    0.06
    Act Density 0.002%

    No Known Activations