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

    Neuronpedia

    INDEX
    Explanations

    concepts related to belief systems and their logical implications

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

    science and scientific research

    np_acts-logits-general · gemini-2.0-flash

    empirical research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.57
    Koordin
    -0.51
     CanadaChoose
    -0.48
     AssemblyProduct
    -0.48
    jacency
    -0.48
     inflater
    -0.46
     NUKAT
    -0.46
    nościo
    -0.46
    ján
    -0.45
    JoinColumn
    -0.44
    POSITIVE LOGITS
     scientific
    1.17
     empirical
    1.06
    scientific
    1.00
     science
    0.98
     sciences
    0.92
     científico
    0.92
     epistem
    0.92
     scientists
    0.90
    empi
    0.86
    Scientific
    0.85
    Act Density 0.700%

    No Known Activations