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

    Neuronpedia

    INDEX
    Explanations

    among

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    римін
    -0.07
    Як
    -0.07
     butter
    -0.06
     grat
    -0.06
    ніч
    -0.06
    acement
    -0.06
     vm
    -0.06
    .FETCH
    -0.06
     ANSI
    -0.06
    .|
    -0.06
    POSITIVE LOGITS
    选择
    0.07
    λό
    0.07
     glands
    0.06
    _ranges
    0.06
     này
    0.06
     individually
    0.06
     Interface
    0.06
    -example
    0.06
     lãnh
    0.06
    名無し
    0.06
    Act Density 0.000%

    No Known Activations