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

    Neuronpedia

    INDEX
    Explanations

    references to different stages or levels of disease or treatment protocols

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

    "Stage" followed by Roman numerals or related terms

    np_acts-logits-general · gemini-2.0-flash

    stage levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %)$
    -0.54
     siden
    -0.54
     murm
    -0.51
     Freitas
    -0.50
    RetentionPolicy
    -0.50
    クト
    -0.50
    Ther
    -0.49
    ran
    -0.49
     magasiner
    -0.49
    graphiques
    -0.48
    POSITIVE LOGITS
     STAGE
    1.07
     Stage
    1.04
    Stage
    0.95
    STAGE
    0.95
     stage
    0.94
     stages
    0.93
    Stages
    0.91
     Stages
    0.91
    stage
    0.90
    stages
    0.85
    Act Density 0.147%

    No Known Activations