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

    Neuronpedia

    INDEX
    Explanations

    asked

    np_max-act · gemini-2.0-flash

    This neuron detects instances where participants are being “asked” to respond or perform tasks (e.g., survey/interview prompts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pigs
    -0.08
     regist
    -0.07
     mnoh
    -0.07
     Vie
    -0.07
     exemplo
    -0.07
    mos
    -0.07
     mart
    -0.07
    �
    -0.07
    tail
    -0.07
    fort
    -0.07
    POSITIVE LOGITS
    Asked
    0.06
     القد
    0.06
     asked
    0.06
    ....↵↵
    0.06
    	LCD
    0.06
     встанов
    0.06
     writeFile
    0.06
     Asked
    0.06
    stackoverflow
    0.06
    ..↵↵
    0.06
    Act Density 0.027%

    No Known Activations