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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to programming and technical instructions

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

    after certain verbs ("is", "are")

    np_acts-logits-general · gemini-2.0-flash

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wiktionnaire
    -0.68
    ſicht
    -0.66
     kasarigan
    -0.64
    RTLR
    -0.64
     Waſſer
    -0.62
     SqlParameter
    -0.62
    下载附件
    -0.60
    ⟬
    -0.60
    ロウィン
    -0.60
     ſeine
    -0.60
    POSITIVE LOGITS
     typelib
    0.43
     These
    0.33
     these
    0.32
     بخ
    0.30
    好
    0.30
     بنا
    0.29
     noce
    0.29
    нин
    0.28
    стоя
    0.27
     The
    0.27
    Act Density 0.548%

    No Known Activations