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

    Neuronpedia

    INDEX
    Explanations

    statements related to empirical evidence and scientific reasoning

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

    science or the scientific method

    np_acts-logits-general · gemini-2.0-flash

    science and experiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.69
    urlpatterns
    -0.64
    ustain
    -0.57
     entretien
    -0.56
    djangoproject
    -0.56
     opérateur
    -0.52
     CanadaChoose
    -0.52
    도록
    -0.51
    المشاركات
    -0.51
     visibilité
    -0.51
    POSITIVE LOGITS
     scientific
    1.29
    scientific
    1.12
     science
    1.07
     científico
    1.03
     scientifique
    1.00
     Scientific
    0.99
     scienti
    0.98
    Scientific
    0.96
     scientists
    0.95
     científica
    0.94
    Act Density 0.715%

    No Known Activations