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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and present tense forms of the verb "to be."

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

    je suis (I am)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.57
    \{\\
    -0.52
    __(/*!
    -0.50
     Constipation
    -0.49
    acken
    -0.47
     Wiktionnaire
    -0.47
     дописавши
    -0.47
    -------
    -0.47
    ourtney
    -0.47
    Cactus
    -0.46
    POSITIVE LOGITS
     هو
    1.52
     هي
    1.30
     وهو
    1.09
    هو
    1.00
     وهي
    0.92
     הוא
    0.89
     היא
    0.82
     هيا
    0.73
    هي
    0.73
     שהוא
    0.72
    Act Density 0.001%

    No Known Activations