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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate direct influence or responsibility in a context

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

    directly followed by actions or effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meninos
    -0.51
    retudo
    -0.46
    ambién
    -0.45
     JpaRepository
    -0.43
     adesivos
    -0.42
    mejores
    -0.42
     sécurisé
    -0.42
     trânsito
    -0.42
     réservé
    -0.42
     dasarnya
    -0.42
    POSITIVE LOGITS
     directly
    0.94
     direct
    0.84
     Directly
    0.80
    Direct
    0.79
    direct
    0.79
    directly
    0.78
    直接
    0.75
     directe
    0.70
     indirect
    0.70
     direkten
    0.68
    Act Density 0.026%

    No Known Activations