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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τεύ
    -0.08
    Drive
    -0.07
    .transactions
    -0.07
     体
    -0.06
     Hyderabad
    -0.06
    Ан
    -0.06
    }.{
    -0.06
     '.'
    -0.06
     panic
    -0.06
    結果
    -0.06
    POSITIVE LOGITS
    ytt
    0.08
     щоб
    0.07
    "↵
    0.06
     Osc
    0.06
     شرکت
    0.06
     Dave
    0.06
     ONLINE
    0.06
     Danny
    0.06
    bast
    0.06
    Под
    0.06
    Act Density 0.013%

    No Known Activations