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

    Neuronpedia

    INDEX
    Explanations

    structured document elements such as paragraphs and sections

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

    legal citations and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndContext
    -0.64
    ArgumentParser
    -0.54
    spender
    -0.51
    EDEFAULT
    -0.48
    存于互联网档案馆
    -0.48
     gyhoeddwyd
    -0.47
    utilisons
    -0.46
    WebElementEntity
    -0.45
    GEBURTSDATUM
    -0.45
     AssemblyCulture
    -0.44
    POSITIVE LOGITS
     both
    0.56
     Drs
    0.54
     Messrs
    0.50
     både
    0.48
    both
    0.47
     zowel
    0.44
    ::{
    0.43
    ParallelGroup
    0.43
     BOTH
    0.42
     §§
    0.42
    Act Density 0.146%

    No Known Activations