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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the difficulty level of tasks or experiences

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

    easy, simple, hard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.73
     disambiguazione
    -0.63
     Paglinawan
    -0.62
     يتيمه
    -0.60
    IMPORTED
    -0.56
     AssemblyCulture
    -0.56
    IntoConstraints
    -0.55
     AssemblyCompany
    -0.54
     betweenstory
    -0.54
     незавершена
    -0.53
    POSITIVE LOGITS
     easy
    2.58
    easy
    2.41
    Easy
    2.33
     Easy
    2.23
     easier
    2.08
     EASY
    2.06
    EASY
    1.95
     fácil
    1.95
     easiest
    1.87
     fáciles
    1.84
    Act Density 0.132%

    No Known Activations