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

    Neuronpedia

    INDEX
    Explanations

    words used in scientific writing to describe studies, results, and justifications

    oai_token-act-pair · gemini-2.0-flash

    scientific/medical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     calendriers
    -0.89
    enumi
    -0.80
    ########.
    -0.79
     ujednoznacz
    -0.76
     propOrder
    -0.73
    ंदीखरीदारी
    -0.72
     IndexPath
    -0.69
    KURZBESCHREIBUNG
    -0.68
    verwijspagina
    -0.67
     snippetHide
    -0.65
    POSITIVE LOGITS
    ...
    0.50
    …
    0.47
    //
    0.43
    掛け
    0.42
     intens
    0.42
    Next
    0.41
     multiple
    0.41
    mos
    0.41
     walking
    0.41
    🧪
    0.41
    Act Density 5.641%

    No Known Activations