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

    Neuronpedia

    INDEX
    Explanations

    pronouns and words relating to identity

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

    when followed by it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.69
     Staates
    -0.53
     jugement
    -0.52
     createState
    -0.50
     règlement
    -0.47
    AndroidJUnit
    -0.46
    itinéraire
    -0.45
     cuota
    -0.45
     IBRARY
    -0.43
     répertoire
    -0.43
    POSITIVE LOGITS
    :✨
    0.47
     ویکی‌پدی
    0.44
    ьажоргаш
    0.41
    الدراسه
    0.41
     Вікі
    0.41
     nakalista
    0.38
    UnsafeEnabled
    0.38
     BnF
    0.37
     виправивши
    0.37
    ops
    0.35
    Act Density 0.050%

    No Known Activations