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

    Neuronpedia

    INDEX
    Explanations

    device connection

    np_max-act · gemini-2.0-flash

    The neuron fires on imperative instruction phrases (e.g., “Plug … into …,” “Connect your …,” “Insert the …”), identifying step‐by‐step command verbs in procedural how-to directions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    undler
    -0.07
     Dame
    -0.07
    cj
    -0.06
     Gaussian
    -0.06
    	short
    -0.06
     Ventura
    -0.06
     दल
    -0.06
    .vendor
    -0.06
    _rsa
    -0.06
    _boundary
    -0.06
    POSITIVE LOGITS
    gricult
    0.07
     compartment
    0.06
    .isConnected
    0.06
     micro
    0.06
    异
    0.06
     исследования
    0.06
    来了
    0.06
    Development
    0.06
    charger
    0.06
     decoding
    0.06
    Act Density 0.009%

    No Known Activations