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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Post
    -0.07
     Harrison
    -0.07
     flips
    -0.07
    consumer
    -0.07
    filePath
    -0.07
     QDateTime
    -0.06
     Jihad
    -0.06
     posting
    -0.06
     inference
    -0.06
     Исп
    -0.06
    POSITIVE LOGITS
     Unblock
    0.07
     rozs
    0.07
     inhab
    0.06
    	TokenName
    0.06
     motivated
    0.06
     привы
    0.06
    enses
    0.06
    рій
    0.06
     oznám
    0.06
    обов
    0.06
    Act Density 0.085%

    No Known Activations