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

    Neuronpedia

    INDEX
    Explanations

    numbers three to five

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nothrow
    -0.07
    xFB
    -0.07
    أ
    -0.07
    ilere
    -0.07
     losers
    -0.06
     examine
    -0.06
     безопас
    -0.06
    �
    -0.06
    .XPATH
    -0.06
     Lu
    -0.06
    POSITIVE LOGITS
    ellites
    0.06
     apply
    0.06
     cuatro
    0.06
     Habit
    0.06
    -distance
    0.06
    .CreateTable
    0.06
    =wx
    0.06
    ptions
    0.06
     local
    0.06
    -hard
    0.06
    Act Density 0.014%

    No Known Activations