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

    Neuronpedia

    INDEX
    Explanations

    ify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wlan
    -0.08
     integrates
    -0.07
     his
    -0.07
     written
    -0.07
     aff
    -0.07
    _blue
    -0.07
     todd
    -0.07
    寻
    -0.07
    ធ
    -0.07
     iod
    -0.07
    POSITIVE LOGITS
    フェ
    0.07
    ------↵
    0.07
    0.07
     ApiResponse
    0.07
     Rx
    0.07
    Nx
    0.07
    simple
    0.07
    鬏
    0.07
    abox
    0.07
     Dish
    0.06
    Act Density 0.002%

    No Known Activations