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

    Neuronpedia

    INDEX
    Explanations

    determine know

    np_max-act · gemini-2.0-flash

    This neuron detects question-oriented language—words and phrases like “determine,” “is there,” “how,” or “know” that signal an interrogative intent.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     palabras
    -0.07
    employees
    -0.07
    Fetch
    -0.06
    午
    -0.06
    approved
    -0.06
     cosmos
    -0.06
    .img
    -0.06
     chambers
    -0.06
    ware
    -0.06
    sembler
    -0.06
    POSITIVE LOGITS
     výši
    0.07
    �
    0.07
    .PropTypes
    0.07
    �
    0.07
     ay
    0.07
     مفهوم
    0.07
     začátku
    0.07
    џџџџџџџџ
    0.06
     useHistory
    0.06
     lange
    0.06
    Act Density 0.048%

    No Known Activations