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

    Neuronpedia

    INDEX
    Explanations

    sorry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    logged
    -0.06
     Minister
    -0.06
     unveiled
    -0.06
     Españ
    -0.06
    Ub
    -0.06
    wheel
    -0.06
     entreg
    -0.06
     경험
    -0.06
    perience
    -0.06
    .live
    -0.06
    POSITIVE LOGITS
     Sorry
    0.09
    Sorry
    0.08
    sorry
    0.08
     sorry
    0.07
     dry
    0.07
     fault
    0.07
    　ヽ
    0.06
     い
    0.06
     اروپ
    0.06
    ος
    0.06
    Act Density 0.009%

    No Known Activations