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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and linking words in text

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

    Followed by common French/Spanish words

    np_acts-logits-general · gemini-2.0-flash

    French conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anſ
    -1.01
     Theſe
    -0.96
     purpoſe
    -0.89
     raiſ
    -0.89
     Inſ
    -0.89
     viſ
    -0.83
     Perſ
    -0.83
     faſt
    -0.82
     ſou
    -0.82
     ſmall
    -0.81
    POSITIVE LOGITS
    出版年
    0.81
    CppCodeGen
    0.69
    iettivo
    0.67
    homonymie
    0.67
    WebElementEntity
    0.64
     nakalista
    0.63
     дописавши
    0.62
    ProcessEvent
    0.60
     thiệu
    0.60
    uitton
    0.59
    Act Density 0.056%

    No Known Activations