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

    Neuronpedia

    INDEX
    Explanations

    beginnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rupture
    -0.09
     شرایط
    -0.08
    payments
    -0.08
    merge
    -0.08
     Lease
    -0.08
    pring
    -0.08
     cuales
    -0.07
     refunds
    -0.07
     Dent
    -0.07
     changements
    -0.07
    POSITIVE LOGITS
    童
    0.12
     extracurricular
    0.11
     childhood
    0.11
     hobby
    0.11
    孩
    0.11
     enthusiasts
    0.11
    兴趣
    0.11
     hobbies
    0.10
     علاقه
    0.10
     enthusiast
    0.10
    Act Density 0.102%

    No Known Activations