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

    Neuronpedia

    INDEX
    Explanations

    theoretical math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蒙
    -0.06
     franca
    -0.06
     віз
    -0.06
    xeb
    -0.06
    598
    -0.06
     Dul
    -0.06
    ,,,
    -0.06
    729
    -0.06
     subdiv
    -0.06
    773
    -0.06
    POSITIVE LOGITS
    mage
    0.06
    ,user
    0.06
     erotisk
    0.06
     Xã
    0.06
    .Logging
    0.06
     amigo
    0.06
    (dev
    0.06
    وتی
    0.06
     Dhabi
    0.06
     Sets
    0.06
    Act Density 0.054%

    No Known Activations