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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns

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

    by itself or themselves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     epä
    -0.41
    GoogleApiClient
    -0.41
    Šaltiniai
    -0.38
     énergétique
    -0.37
     gewisser
    -0.37
    noopener
    -0.36
     souhaitez
    -0.36
     frühen
    -0.36
     jää
    -0.35
    تقاوى
    -0.35
    POSITIVE LOGITS
    Alone
    0.59
     Alone
    0.57
    alone
    0.56
     referrerpolicy
    0.56
     CreateTagHelper
    0.54
     thiệu
    0.54
    bigger
    0.51
    AsUp
    0.50
    gola
    0.50
    Bigger
    0.50
    Act Density 0.003%

    No Known Activations