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

    Neuronpedia

    INDEX
    Explanations

    phrases concerning medical treatment outcomes and their consistency over time

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

    Something "remains" or "stays"

    np_acts-logits-general · gemini-2.0-flash

    continue to exist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -0.69
    antMatchers
    -0.57
    ็จ
    -0.56
    انيف
    -0.54
    protoc
    -0.50
     NSCoder
    -0.48
    medik
    -0.48
    Formerly
    -0.46
    ftagPool
    -0.46
    ברת
    -0.44
    POSITIVE LOGITS
     remain
    2.06
     retained
    2.04
     stay
    2.03
     retain
    2.02
     stays
    2.00
     staying
    1.99
     retaining
    1.98
     remained
    1.98
     stayed
    1.97
     continue
    1.91
    Act Density 0.938%

    No Known Activations