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

    Neuronpedia

    INDEX
    Explanations

    locations/organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [href
    -0.06
     Кроме
    -0.06
     appe
    -0.06
    _INCLUDE
    -0.06
     Indicates
    -0.06
    "d
    -0.06
    (Employee
    -0.06
     determine
    -0.06
    Special
    -0.06
     if
    -0.06
    POSITIVE LOGITS
    runs
    0.07
    ICLES
    0.07
    ۱
    0.07
    �
    0.06
     прев
    0.06
    751
    0.06
     맡
    0.06
     Rena
    0.06
     dereg
    0.06
     строитель
    0.06
    Act Density 0.044%

    No Known Activations