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

    Neuronpedia

    INDEX
    Explanations

    Computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蔟
    -0.08
    人群
    -0.07
     Prescription
    -0.07
    深厚
    -0.07
     char
    -0.07
     mascot
    -0.06
     
    -0.06
    woff
    -0.06
     ascertain
    -0.06
    战组合
    -0.06
    POSITIVE LOGITS
     Liberals
    0.07
    耒
    0.07
     Signup
    0.07
     flexible
    0.07
     #(
    0.06
     issuance
    0.06
    .display
    0.06
     taller
    0.06
     זקוק
    0.06
    dh
    0.06
    Act Density 0.056%

    No Known Activations