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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to legal and diagnostic concepts, particularly focusing on false positives, arrests, and negative outcomes

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

    false positive, false negative, false arrest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cells
    -0.45
     normally
    -0.38
     patients
    -0.36
     growing
    -0.35
     normal
    -0.34
     prior
    -0.33
     civil
    -0.31
     directly
    -0.31
     vit
    -0.30
     conventional
    -0.30
    POSITIVE LOGITS
     falsa
    0.93
     fausse
    0.90
     falsas
    0.87
     falsos
    0.87
     falso
    0.86
    false
    0.77
    False
    0.75
     false
    0.73
     palsu
    0.70
     falsche
    0.68
    Act Density 0.036%

    No Known Activations