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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    The neuron detects the presence of questions or question‐like phrasing (e.g. interrogative words and question marks).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     र
    -0.06
    ॉर
    -0.06
    ÓN
    -0.06
     componentWillMount
    -0.06
     unaware
    -0.06
     summarizes
    -0.06
     Bird
    -0.06
     �
    -0.05
    achts
    -0.05
     deleted
    -0.05
    POSITIVE LOGITS
     Styled
    0.07
     evalu
    0.07
     انتظ
    0.07
     उठ
    0.07
    τικής
    0.07
    elli
    0.07
    tainment
    0.07
    stripe
    0.07
    _TIMESTAMP
    0.06
    bron
    0.06
    Act Density 0.067%

    No Known Activations