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

    Neuronpedia

    INDEX
    Explanations

    Quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Firewall
    -0.08
    requ
    -0.07
    Ing
    -0.07
     oran
    -0.06
    paralle
    -0.06
    brains
    -0.06
     па
    -0.06
     '<%=
    -0.06
     таком
    -0.06
     Zd
    -0.06
    POSITIVE LOGITS
    isión
    0.07
    ENARIO
    0.06
     Глав
    0.06
     secrets
    0.06
    (metadata
    0.06
     WiFi
    0.06
     Permission
    0.06
     listen
    0.06
     marched
    0.06
    .close
    0.06
    Act Density 0.004%

    No Known Activations