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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OPC
    -0.07
     coax
    -0.07
     RNG
    -0.07
     Sá
    -0.07
     explosive
    -0.07
     Rollen
    -0.07
     triglycer
    -0.07
    roog
    -0.07
     붙
    -0.07
     gc
    -0.06
    POSITIVE LOGITS
    反馈
    0.13
    意见
    0.12
     grievances
    0.10
    feedback
    0.10
    投诉
    0.10
     പരാത
    0.10
     의견
    0.10
    _feedback
    0.10
    ความคิดเห็น
    0.10
     услыш
    0.10
    Act Density 0.020%

    No Known Activations