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

    Neuronpedia

    INDEX
    Explanations

    message data or structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meaningless
    1.12
    manship
    1.09
    л
    1.05
    та
    1.04
    neath
    1.03
    makedirs
    1.00
     nightmares
    1.00
    ctions
    0.99
    ूहिक
    0.98
    း
    0.96
    POSITIVE LOGITS
    बारक
    1.10
     അയ
    1.09
    繧
    1.09
     déliv
    1.08
    वाहक
    1.08
     sent
    1.07
     ciała
    1.07
     föld
    1.04
    ことは
    1.03
     envía
    1.03
    Act Density 0.082%

    No Known Activations