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

    Neuronpedia

    INDEX
    Explanations

    terms related to personal identifiers or references in communication

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

    Romance language determiners and pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Viitteet
    -0.50
     arşivlendi
    -0.49
    $_['
    -0.46
     Khat
    -0.44
    tschafts
    -0.44
     pluck
    -0.44
     plu
    -0.43
    geo
    -0.43
    GenerationType
    -0.43
     пользу
    -0.43
    POSITIVE LOGITS
     autorytatywna
    0.90
    endwhile
    0.43
    them
    0.43
    เธอ
    0.43
     them
    0.40
    ándolos
    0.39
    .*")]
    0.39
    Mereka
    0.39
    arlos
    0.39
    Witaj
    0.39
    Act Density 0.003%

    No Known Activations