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

    Neuronpedia

    INDEX
    Explanations

    firewall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dni
    -0.07
    มาย
    -0.07
    ('{}
    -0.06
     têm
    -0.06
     cela
    -0.06
     pomáh
    -0.06
     />)↵
    -0.06
    撰
    -0.06
    げ
    -0.06
     соч
    -0.06
    POSITIVE LOGITS
     firewall
    0.13
     Firewall
    0.09
    ACL
    0.08
     bestselling
    0.07
     Router
    0.07
    washer
    0.07
     heals
    0.07
     freeze
    0.07
     router
    0.07
     Wong
    0.06
    Act Density 0.001%

    No Known Activations