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

    Neuronpedia

    INDEX
    Explanations

    references to significant quantities or values within various contexts

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

    Follows indefinite article or demonstrative pronoun

    np_acts-logits-general · gemini-2.0-flash

    a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.70
    $_['
    -0.68
    twimg
    -0.68
    ]-->
    -0.64
    jsonwebtoken
    -0.59
    DispatchToProps
    -0.59
    saraba
    -0.58
    oa̍t
    -0.57
    abestanden
    -0.57
    GeneratedValue
    -0.56
    POSITIVE LOGITS
    jectures
    0.55
     Efq
    0.52
     Monfieur
    0.51
    atzes
    0.50
    gnition
    0.50
    testens
    0.48
     thoſe
    0.48
    zbęd
    0.48
     Chrif
    0.47
    })`
    0.47
    Act Density 0.048%

    No Known Activations