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

    Neuronpedia

    INDEX
    Explanations

    -->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verv
    -0.06
    ｡
    -0.06
     характер
    -0.06
    Dry
    -0.06
     sık
    -0.06
     cloned
    -0.06
     thinly
    -0.06
    无法
    -0.06
    @Inject
    -0.06
     parcel
    -0.06
    POSITIVE LOGITS
     predictive
    0.07
    (/
    0.07
    bios
    0.07
     diplomats
    0.06
    .Inventory
    0.06
    velocity
    0.06
     bells
    0.06
    latitude
    0.06
     ///↵
    0.06
    IAL
    0.06
    Act Density 0.001%

    No Known Activations