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

    Neuronpedia

    INDEX
    Explanations

    opportunity or privilege

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resisting
    -0.06
    ิวเตอร
    -0.06
    "class
    -0.06
    opic
    -0.06
     Conte
    -0.06
    .NORMAL
    -0.06
     "$
    -0.05
    /filter
    -0.05
    Computer
    -0.05
     refill
    -0.05
    POSITIVE LOGITS
    ฑ
    0.07
    /www
    0.07
     zamanda
    0.07
     Keto
    0.07
    _firstname
    0.07
    ;
↵
↵
↵
↵
    0.07
     allows
    0.07
     impactful
    0.07
     kari
    0.07
    ")]
    0.06
    Act Density 0.013%

    No Known Activations