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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment toward energy companies and cost of living

    oai_token-act-pair · gemini-2.0-flash

    utilities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poils
    -0.46
     cargas
    -0.45
     peine
    -0.45
     spéciaux
    -0.44
     الرحمن
    -0.44
     détach
    -0.42
     conversión
    -0.41
     peines
    -0.41
     asiento
    -0.41
     kife
    -0.41
    POSITIVE LOGITS
     utilities
    0.96
     heating
    0.90
     utility
    0.88
     Heating
    0.82
    utilities
    0.81
    Heating
    0.80
     Utilities
    0.79
    heating
    0.78
    utility
    0.74
    ExecuteReader
    0.73
    Act Density 1.313%

    No Known Activations