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

    Neuronpedia

    INDEX
    Explanations

    questions and considerations regarding choice and responsibility

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

    asking how to perform

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences that ask questions, especially "how"‑style interrogative phrases (question words and the following verbs).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.70
     MainAxisSize
    -0.68
    Jereo
    -0.68
     propOrder
    -0.64
    новниш
    -0.63
     שוליים
    -0.61
    FormTagHelper
    -0.60
    FailureListener
    -0.59
    usercontent
    -0.57
    RectangleBorder
    -0.56
    POSITIVE LOGITS
    ?’
    0.58
    ?”
    0.57
    ?
    0.55
    }?
    0.51
    ?”.
    0.51
    ?"
    0.51
    %?
    0.50
    ?).
    0.49
    ?'
    0.48
    ؟
    0.48
    Act Density 0.073%

    No Known Activations