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

    Neuronpedia

    INDEX
    Explanations

    connect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     своїм
    -0.07
     phenomen
    -0.07
    али
    -0.07
    _raise
    -0.06
    	on
    -0.06
    (Note
    -0.06
     being
    -0.06
    ,[
    -0.06
    appers
    -0.06
    _inv
    -0.06
    POSITIVE LOGITS
     trimmed
    0.07
     treadmill
    0.07
     Chicago
    0.07
    Urls
    0.07
     Budapest
    0.06
     Buenos
    0.06
     Detroit
    0.06
     Medicare
    0.06
     Uruguay
    0.06
     privately
    0.06
    Act Density 0.014%

    No Known Activations