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

    Neuronpedia

    INDEX
    Explanations

    open parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ايش
    -0.07
     cervical
    -0.07
     nostalgia
    -0.07
     behavioral
    -0.06
    ,left
    -0.06
     xls
    -0.06
    ifestyle
    -0.06
     EA
    -0.06
    Driver
    -0.06
     žen
    -0.06
    POSITIVE LOGITS
    ("/{
    0.06
     thép
    0.06
     склад
    0.06
    倒
    0.06
    .IS
    0.06
     документ
    0.06
    628
    0.06
    —↵↵
    0.06
    ']").
    0.06
     estimated
    0.06
    Act Density 0.006%

    No Known Activations