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

    Neuronpedia

    INDEX
    Explanations

    names of persons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restraining
    -0.07
    ザ
    -0.06
    _NOTIFICATION
    -0.06
     laundry
    -0.06
     Producto
    -0.06
    _yes
    -0.06
     injunction
    -0.06
    _expect
    -0.06
    出した
    -0.06
     πρώτη
    -0.06
    POSITIVE LOGITS
     sinh
    0.06
    ابل
    0.06
    .Component
    0.06
    _archive
    0.06
     exported
    0.06
    (Db
    0.06
    美國
    0.06
     spor
    0.06
     baj
    0.06
     덤프
    0.06
    Act Density 0.026%

    No Known Activations