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

    Neuronpedia

    INDEX
    Explanations

    technical passages that describe a phenomenon and people who make decisions

    oai_token-act-pair · gemini-2.0-flash

    Scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     final
    -2.64
     finally
    -2.64
     ultimately
    -2.53
    final
    -2.44
     Finally
    -2.38
     finalmente
    -2.38
    finally
    -2.34
    Finally
    -2.33
    Final
    -2.31
     Final
    -2.31
    POSITIVE LOGITS
     esternos
    0.69
     дописавши
    0.67
    0.60
    asjons
    0.58
    చ
    0.57
    Biographie
    0.56
     disambiguazione
    0.55
    sizeCache
    0.55
     متعلقه
    0.54
    GoogleApiClient
    0.53
    Act Density 5.486%

    No Known Activations