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

    Neuronpedia

    INDEX
    Explanations

    references to the pronouns "he" and "she."

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

    pronoun she

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.47
     lendemain
    -0.42
     éte
    -0.41
     invasión
    -0.38
     Paramètres
    -0.35
    Obrázky
    -0.34
     rénovation
    -0.33
     malgré
    -0.33
     kinda
    -0.33
     besos
    -0.32
    POSITIVE LOGITS
     CURIAM
    0.85
    ſelf
    0.63
    MLLoader
    0.61
    Personendaten
    0.59
     she
    0.57
    Она
    0.56
    GraphicsUnit
    0.55
     Rptr
    0.54
     она
    0.53
     Савезне
    0.53
    Act Density 0.004%

    No Known Activations