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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash

    This neuron detects polite instructional cues—words like “Please” or “Click” that introduce a request or command.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     weekly
    -0.06
     siz
    -0.06
    SSF
    -0.06
     Studi
    -0.06
    910
    -0.06
     мов
    -0.06
     seekers
    -0.06
     businesses
    -0.06
    Places
    -0.06
     logits
    -0.06
    POSITIVE LOGITS
     прям
    0.07
    /on
    0.07
     rainy
    0.06
    �
    0.06
    فی
    0.06
    PLICATE
    0.06
     DateTimeKind
    0.06
    ріб
    0.06
     {%
    0.06
     효
    0.06
    Act Density 0.172%

    No Known Activations