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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash

    This neuron detects the start of an instructional prompt phrase (e.g. “Use the following…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     humorous
    -0.07
     BEL
    -0.07
    _reason
    -0.06
     recounts
    -0.06
     Jan
    -0.06
    _val
    -0.06
    mort
    -0.06
    ตอบ
    -0.06
    关键
    -0.06
     hateful
    -0.06
    POSITIVE LOGITS
     بررسی
    0.07
    ’util
    0.06
    Bạn
    0.06
    bbb
    0.06
     minib
    0.06
     onMouse
    0.06
    	NullCheck
    0.06
    [Boolean
    0.06
    　�
    0.06
    �
    0.06
    Act Density 0.026%

    No Known Activations