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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptions of size and records

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

    records and superlatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :+:
    -0.42
     تانيه
    -0.40
    WithIOException
    -0.39
    -------------</
    -0.38
    rophoresis
    -0.37
     litté
    -0.36
    iodía
    -0.36
     bandeja
    -0.35
     propOrder
    -0.35
     tű
    -0.34
    POSITIVE LOGITS
     Guinness
    0.57
    Toponymie
    0.47
     рекор
    0.47
    IUrlHelper
    0.47
    Largest
    0.47
     rekord
    0.46
     record
    0.46
     largest
    0.45
     world
    0.44
    記録
    0.42
    Act Density 0.043%

    No Known Activations