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

    Neuronpedia

    INDEX
    Explanations

    questions, particularly those that inquire about reasons, methods, or details about processes and practices

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

    question words and punctuation

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

    the presence of interrogative (WH) question words/phrases indicating a question.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    InjectMocks
    -0.72
     increí
    -0.62
    findpost
    -0.57
     Monfieur
    -0.56
     $_"
    -0.56
     indígen
    -0.53
    webtoken
    -0.52
     incrí
    -0.52
     AppCompatTheme
    -0.52
     témoig
    -0.52
    POSITIVE LOGITS
    ?
    0.52
    ()?
    0.47
    Referencie
    0.43
    ?:
    0.41
     umowy
    0.39
    ？
    0.39
    Referencer
    0.38
    ?=
    0.36
    /?
    0.36
    хьтан
    0.35
    Act Density 0.041%

    No Known Activations