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

    Neuronpedia

    INDEX
    Explanations

    Varied topics

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of machine-learning models or specific neural network architectures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    commended
    -0.07
    �
    -0.07
    比
    -0.07
    tracking
    -0.07
     sunday
    -0.07
     Jag
    -0.06
     Laurie
    -0.06
    ARED
    -0.06
    attice
    -0.06
    sur
    -0.06
    POSITIVE LOGITS
     terra
    0.07
    ANDARD
    0.06
     memcmp
    0.06
    	memset
    0.06
    케이
    0.06
    .example
    0.06
     c
    0.06
    률
    0.06
    خصوص
    0.06
     USSR
    0.06
    Act Density 0.348%

    No Known Activations