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
     له
    -0.07
    startdate
    -0.07
    าตร
    -0.07
    ほ
    -0.06
     нія
    -0.06
     Мор
    -0.06
    -0.06
     اهل
    -0.06
    신청
    -0.06
    できない
    -0.06
    POSITIVE LOGITS
    BOARD
    0.07
    settings
    0.07
    Indices
    0.07
    std
    0.06
     comic
    0.06
    Dem
    0.06
     comics
    0.06
     demographic
    0.06
     Exercises
    0.06
     synt
    0.06
    Act Density 0.002%

    No Known Activations