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

    Neuronpedia

    INDEX
    Explanations

    clean

    np_max-act · gemini-2.0-flash

    steps and processes related to building machine learning models from data.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates for terms describing data‐preparation operations—e.g. data manipulation, cleaning, filtering, preprocessing steps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	st
    -0.07
    simulation
    -0.06
    _measurement
    -0.06
     vault
    -0.06
     beach
    -0.06
    986
    -0.06
    output
    -0.06
     nominated
    -0.06
    	record
    -0.06
     temperatures
    -0.06
    POSITIVE LOGITS
    ngoing
    0.06
     기간
    0.06
    Connell
    0.06
    ети
    0.06
    ιν
    0.06
    .;.;
    0.06
     Humph
    0.06
     الحرب
    0.06
    	pthread
    0.06
    žitě
    0.06
    Act Density 0.016%

    No Known Activations