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

    Neuronpedia

    INDEX
    Explanations

    legal and contract-related terminology

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

    Tokens after periods, commas, or legal terms

    np_acts-logits-general · gemini-2.0-flash

    law and license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.53
      
    -0.51
    ↵↵↵
    -0.50
    ful
    -0.47
    ham
    -0.45
    ine
    -0.44
    ase
    -0.44
        
    -0.43
    al
    -0.43
    <u>
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    1.15
     дописавши
    0.95
     للمعارف
    0.95
     autorytatywna
    0.91
     تانيه
    0.88
     bezeichneter
    0.85
    verwijspagina
    0.84
    .*")]
    0.81
     متعلقه
    0.80
    +#+#
    0.79
    Act Density 0.015%

    No Known Activations