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

    Neuronpedia

    INDEX
    Explanations

    text right before descriptions of going to sleep

    oai_token-act-pair · gemini-2.0-flash

    bed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.68
    AndEndTag
    -0.67
    tagext
    -0.67
    
    -0.66
     postIndex
    -0.62
     contextLoads
    -0.62
    MemoryWarning
    -0.62
    AsUp
    -0.61
    harusnya
    -0.59
    verwijspagina
    -0.59
    POSITIVE LOGITS
     bed
    1.55
    bed
    1.18
     Bed
    1.14
     BED
    1.10
    Bed
    1.09
     beds
    0.96
    BED
    0.88
    beds
    0.85
     Beds
    0.79
     cama
    0.73
    Act Density 0.628%

    No Known Activations