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

    Neuronpedia

    INDEX
    Explanations

    writing about topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Domain
    0.75
     যতটুকু
    0.74
    domain
    0.72
     domain
    0.71
     Domain
    0.70
    extrémité
    0.69
    当該
    0.65
     செயல்படுத்த
    0.65
    业内
    0.65
    AMPLE
    0.64
    POSITIVE LOGITS
     loneliness
    1.83
     love
    1.83
     happiness
    1.78
     friendship
    1.75
     racism
    1.68
     forgiveness
    1.67
     feminism
    1.67
     fascism
    1.66
     immortality
    1.65
     capitalism
    1.64
    Act Density 0.510%

    No Known Activations