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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    synt
    -0.08
     ferie
    -0.08
     충
    -0.08
     eccentric
    -0.08
    fuck
    -0.08
     byr
    -0.08
     christmas
    -0.08
     capp
    -0.07
    cup
    -0.07
     расстоя
    -0.07
    POSITIVE LOGITS
     cybersecurity
    0.11
     specialties
    0.10
     Bereichen
    0.10
    技能
    0.10
    Cyber
    0.09
     secteurs
    0.09
    科技
    0.09
     specialists
    0.09
     sectors
    0.09
    人才
    0.09
    Act Density 0.069%

    No Known Activations