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

    Neuronpedia

    INDEX
    Explanations

    clinical trials and studies

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is detecting the word "Clinical" when it appears at the beginning of a section in medical or scientific texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     ludicrous
    -1.03
    卺
    -0.98
     horrifying
    -0.98
     unbelievably
    -0.96
     procedimento
    -0.96
    就得
    -0.96
     amazingly
    -0.96
     horrid
    -0.96
     bizarre
    -0.95
    简直
    -0.92
    POSITIVE LOGITS
     trial
    1.60
     trials
    1.51
    trials
    1.41
    Trials
    1.40
    trial
    1.28
     practice
    1.22
     épreuves
    0.96
     manifestation
    0.95
     utility
    0.94
     manifestations
    0.94
    Act Density 0.051%

    No Known Activations