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

    Neuronpedia

    INDEX
    Explanations

    ethics and responsibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irect
    -0.07
     apr
    -0.07
     cocktails
    -0.07
     totalitarian
    -0.06
    /test
    -0.06
     roz
    -0.06
     пад
    -0.06
     southeastern
    -0.06
     اك
    -0.06
    _difference
    -0.06
    POSITIVE LOGITS
    .Selected
    0.06
     loadChildren
    0.06
     كل
    0.06
     treasures
    0.06
     Coupon
    0.06
     imageName
    0.06
    pricing
    0.06
    _SETTING
    0.06
     автомоб
    0.06
    ipples
    0.06
    Act Density 0.011%

    No Known Activations