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

    Neuronpedia

    INDEX
    Explanations

    synchronization and sequence completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     honey
    0.42
     every
    0.41
     Honey
    0.40
     ever
    0.39
     É
    0.39
    Fot
    0.39
    ள்கள்
    0.39
     eels
    0.39
    storybook
    0.39
    vite
    0.38
    POSITIVE LOGITS
    нную
    0.40
    dincer
    0.40
     ನಿಜ
    0.39
    廿
    0.38
    $-$,
    0.38
    synchron
    0.37
     ২১
    0.37
    }~\
    0.37
    ొ
    0.37
     synchronize
    0.36
    Act Density 0.000%

    No Known Activations