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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement or consistency with legal or procedural standards

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

    consistent with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.52
    expandindo
    -0.47
     leçons
    -0.45
     Infór
    -0.45
    PointSize
    -0.45
     Masyarakat
    -0.44
    EndGlobalSection
    -0.43
     unicórnio
    -0.42
     jurado
    -0.41
     étu
    -0.40
    POSITIVE LOGITS
     compatible
    0.88
     consistent
    0.85
     congru
    0.83
    consistent
    0.82
     Consistent
    0.81
     congruent
    0.79
     congruence
    0.78
    compatible
    0.77
     Compatible
    0.77
    Compatible
    0.76
    Act Density 0.178%

    No Known Activations