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

    Neuronpedia

    INDEX
    Explanations

    opinions and perspectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demanda
    0.70
     nicknamed
    0.62
     demand
    0.62
     constantes
    0.62
    eware
    0.61
     advertised
    0.61
    獗
    0.60
     superconductor
    0.59
    Demand
    0.59
    ಾರಿ
    0.59
    POSITIVE LOGITS
     opinions
    2.40
     opinion
    2.29
     Opinions
    2.07
     Opinion
    2.02
     perspectives
    1.90
    opinion
    1.87
     opinião
    1.78
    Opinion
    1.77
     мнение
    1.75
     viewpoints
    1.74
    Act Density 0.655%

    No Known Activations