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

    Neuronpedia

    INDEX
    Explanations

    references to language translation and linguistic diversity

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

    preceding languages

    np_acts-logits-general · gemini-2.0-flash

    languages and their translations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ParallelGroup
    -0.44
     olympiques
    -0.44
     $__
    -0.41
    #+#
    -0.41
    сомо
    -0.39
    MediaStore
    -0.38
    IContainer
    -0.38
    astify
    -0.37
     propOrder
    -0.37
     ועל
    -0.37
    POSITIVE LOGITS
     English
    2.66
    English
    2.32
     english
    2.19
     ENGLISH
    2.03
    english
    1.84
     Spanish
    1.81
    ENGLISH
    1.71
     French
    1.57
    Spanish
    1.55
     Arabic
    1.49
    Act Density 0.598%

    No Known Activations