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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contain
    -0.07
    ana
    -0.06
    -initialized
    -0.06
    RDD
    -0.06
    terior
    -0.06
    중에
    -0.06
    -ok
    -0.06
    属
    -0.06
     currentState
    -0.06
     contains
    -0.06
    POSITIVE LOGITS
    _assignment
    0.07
    (mb
    0.07
    wishlist
    0.07
    _Label
    0.07
    (balance
    0.07
     DateFormatter
    0.07
     ff
    0.07
    (re
    0.06
     ولم
    0.06
     {
↵
↵
    0.06
    Act Density 0.000%

    No Known Activations