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

    Neuronpedia

    INDEX
    Explanations

    references to specific car models and their characteristics

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

    example series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Volkswagen
    -0.37
     adidas
    -0.36
    ディダス
    -0.36
     Airbus
    -0.35
     volvo
    -0.35
     cannabis
    -0.34
    avax
    -0.33
    лея
    -0.33
    JsonIgnore
    -0.33
     Ethereum
    -0.33
    POSITIVE LOGITS
     mijne
    0.75
    rungsseite
    0.75
    enterOuterAlt
    0.63
     beginnetje
    0.62
    posedge
    0.62
    Early
    0.61
    webElementXpaths
    0.61
     Early
    0.60
     EARLY
    0.60
     early
    0.59
    Act Density 0.021%

    No Known Activations