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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that emphasize commonality or shared attributes

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

    Followed by nouns relating to a topic

    np_acts-logits-general · gemini-2.0-flash

    common noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.82
    ForResult
    -0.72
    lognese
    -0.69
     indépendante
    -0.67
    Herzlich
    -0.67
     Memoirs
    -0.66
    DATES
    -0.66
     geweest
    -0.65
     Winkler
    -0.64
    כשיו
    -0.64
    POSITIVE LOGITS
     Common
    1.29
    COMMON
    1.24
     common
    1.23
    Common
    1.22
     COMMON
    1.22
    common
    1.09
     commons
    0.99
     común
    0.92
    Commons
    0.86
     CommonModule
    0.85
    Act Density 0.151%

    No Known Activations