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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "down."

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

    write down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deste
    -0.39
    ExtendWith
    -0.38
     rigue
    -0.36
     Layanan
    -0.35
     uitz
    -0.35
     dedicar
    -0.35
    localtime
    -0.35
     genieten
    -0.33
     cool
    -0.33
     blend
    -0.32
    POSITIVE LOGITS
    colhead
    0.66
     recorder
    0.63
     written
    0.63
     nakalista
    0.60
    xnn
    0.59
    written
    0.57
     recorders
    0.57
    GEBURTSDATUM
    0.57
    исленность
    0.57
    IndentedString
    0.56
    Act Density 0.003%

    No Known Activations