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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating possession or belonging

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

    end of mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.79
     resourceCulture
    -0.78
    tagHelperRunner
    -0.75
    parsedMessage
    -0.72
     يتيمه
    -0.70
    uxxxx
    -0.69
     disambiguazione
    -0.64
    +#+#
    -0.63
    featureID
    -0.61
     nahilalakip
    -0.59
    POSITIVE LOGITS
     hopefully
    0.46
    finally
    0.41
    jalá
    0.40
    Hopefully
    0.40
    usleep
    0.39
     übrigens
    0.39
    SUCCEEDED
    0.38
     hope
    0.38
    Finally
    0.38
    ervo
    0.38
    Act Density 0.012%

    No Known Activations