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

    Neuronpedia

    INDEX
    Explanations

    provided

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /google
    -0.08
    -group
    -0.07
    -linux
    -0.06
    овор
    -0.06
    _table
    -0.06
    ectors
    -0.06
    π
    -0.06
     skateboard
    -0.06
    Sizes
    -0.06
     ι
    -0.06
    POSITIVE LOGITS
    HashSet
    0.07
     miglior
    0.06
     गई
    0.06
     ціл
    0.06
    iotics
    0.06
    rial
    0.06
     Snape
    0.06
    	first
    0.06
     молод
    0.06
     Πανεπ
    0.06
    Act Density 0.001%

    No Known Activations