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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of flushing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    flush

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     objectAtIndex
    -0.42
    ApiProperty
    -0.41
    клопе
    -0.40
    Ragnar
    -0.40
     getItemId
    -0.40
     Parton
    -0.39
    yargs
    -0.38
     BaseController
    -0.38
     Tagore
    -0.38
     représenter
    -0.37
    POSITIVE LOGITS
     flush
    2.38
     Flush
    2.33
    Flush
    2.05
    flush
    2.05
     flushed
    1.89
     flushing
    1.87
    FLUSH
    1.63
     Flushing
    1.51
    ushes
    1.01
     Blush
    0.94
    Act Density 0.003%

    No Known Activations