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

    Neuronpedia

    INDEX
    Explanations

    short descriptions/information

    np_max-act · gemini-2.0-flash

    The neuron detects instruction words in the prompt that tell the model to generate or rewrite text—for example “write,” “short,” “description,” and “headline.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pirate
    -0.07
     LCD
    -0.07
    -and
    -0.06
     refs
    -0.06
    ViewPager
    -0.06
    gcd
    -0.06
    Whenever
    -0.06
    (embed
    -0.06
    (gc
    -0.06
    arged
    -0.06
    POSITIVE LOGITS
    涉
    0.06
     فرمان
    0.06
     JSName
    0.06
      
    0.06
     approve
    0.06
     ΔE
    0.06
    dg
    0.06
    	super
    0.06
     Loren
    0.05
     donna
    0.05
    Act Density 0.005%

    No Known Activations