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

    Neuronpedia

    INDEX
    Explanations

    words ending in "ation", "ion", or "ment", or words related to these endings.

    oai_token-act-pair · gemini-2.0-flash

    negative actions and foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifed
    -0.38
    (
    -0.38
     ne
    -0.37
    ازات
    -0.36
    گاه
    -0.36
    سات
    -0.35
    ிக
    -0.35
    responseType
    -0.35
     is
    -0.35
     will
    -0.35
    POSITIVE LOGITS
    Personendaten
    1.05
    ########.
    0.93
     disambiguazione
    0.84
     EconPapers
    0.81
    drawal
    0.81
    :✨
    0.80
    ubereitung
    0.79
    ----</
    0.79
    0.76
    manufact
    0.76
    Act Density 0.371%

    No Known Activations