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

    Neuronpedia

    INDEX
    Explanations

    determined

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    -develop
    -0.07
     bg
    -0.07
     cors
    -0.07
    小事
    -0.07
     vign
    -0.07
    sg
    -0.07
    ㄺ
    -0.07
     $("<
    -0.07
    为广大
    -0.07
    POSITIVE LOGITS
    .);↵
    0.08
     batteries
    0.08
    цов
    0.07
    Ｕ
    0.07
    _FC
    0.07
    ())
↵
    0.07
    )),↵
    0.07
     На
    0.06
    .Month
    0.06
    午餐
    0.06
    Act Density 0.010%

    No Known Activations