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

    Neuronpedia

    INDEX
    Explanations

    Time and distribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     list
    -0.07
    alarm
    -0.07
    .levels
    -0.07
     Publishers
    -0.07
    odzi
    -0.07
     incomes
    -0.06
    ↵
    -0.06
     страны
    -0.06
    	or
    -0.06
    fails
    -0.06
    POSITIVE LOGITS
    Generator
    0.06
    ,T
    0.06
    �니다
    0.06
     مدت
    0.06
    (errorMessage
    0.06
     Middleton
    0.06
    -type
    0.06
    -Type
    0.05
     currentNode
    0.05
    -ch
    0.05
    Act Density 0.072%

    No Known Activations