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

    Neuronpedia

    INDEX
    Explanations

    cold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /slick
    -0.07
    "/></
    -0.07
     useRouter
    -0.07
    crime
    -0.07
     misd
    -0.07
    toBeInTheDocument
    -0.07
    海上
    -0.06
     shipment
    -0.06
    搭乘
    -0.06
    莪
    -0.06
    POSITIVE LOGITS
     predetermined
    0.08
    冷漠
    0.07
     средне
    0.07
    压制
    0.07
    \">
    0.07
    specs
    0.06
    灰尘
    0.06
    압
    0.06
     requirements
    0.06
     iod
    0.06
    Act Density 0.027%

    No Known Activations