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

    Neuronpedia

    INDEX
    Explanations

    administrator or root privileges needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biographical
    0.68
     Nahr
    0.68
     Norton
    0.66
    ത്രം
    0.65
     Leb
    0.65
     Hương
    0.64
     Biographical
    0.64
     आयोग
    0.64
    ชี
    0.64
     AppleWebKit
    0.63
    POSITIVE LOGITS
    管理员
    1.20
     Administrator
    1.19
    Administrator
    1.14
    Admin
    1.14
     elevados
    1.10
     privileges
    1.10
     administrator
    1.10
     privilege
    1.10
    administrator
    1.09
     elevated
    1.08
    Act Density 0.040%

    No Known Activations