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

    Neuronpedia

    INDEX
    Explanations

    did

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cure
    -0.08
    录
    -0.07
     シ
    -0.06
     some
    -0.06
    یه
    -0.06
     summarizes
    -0.06
    τεύ
    -0.06
     obviously
    -0.06
     Lâm
    -0.06
    瓜
    -0.06
    POSITIVE LOGITS
    onder
    0.07
    .SetText
    0.07
    confirmed
    0.06
    	connection
    0.06
     encoded
    0.06
    shutdown
    0.06
     fields
    0.06
    collection
    0.06
     volumes
    0.06
    	Create
    0.06
    Act Density 0.001%

    No Known Activations