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

    Neuronpedia

    INDEX
    Explanations

    sharing feelings and emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innovación
    0.94
     skyscraper
    0.85
    innov
    0.83
     ingenious
    0.83
     innovation
    0.82
    innovation
    0.79
    postcss
    0.77
     aficionados
    0.77
     innovator
    0.76
     innovators
    0.75
    POSITIVE LOGITS
     hurtful
    1.13
     privacy
    1.00
     hurt
    0.98
     Privacy
    0.96
     upsetting
    0.93
    連絡
    0.92
     confidentiality
    0.91
     texting
    0.90
     Distance
    0.89
    Privacy
    0.89
    Act Density 0.607%

    No Known Activations