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

    Neuronpedia

    INDEX
    Explanations

    computer instructions/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蒻
    -0.08
    個
    -0.07
    纪检监察
    -0.07
     StreamLazy
    -0.07
    ître
    -0.07
     Ан
    -0.07
    主城区
    -0.07
     мен
    -0.07
     Quốc
    -0.07
    确切
    -0.07
    POSITIVE LOGITS
    edy
    0.07
    outcome
    0.07
    .ads
    0.07
    ()."
    0.07
    -power
    0.07
    뜯
    0.06
    فكر
    0.06
    츙
    0.06
     ley
    0.06
    改革
    0.06
    Act Density 0.009%

    No Known Activations