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

    Neuronpedia

    INDEX
    Explanations

    betrayal and broken relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     optimize
    0.57
     iterating
    0.54
     தொழில்நுட்ப
    0.51
     ইউনিক
    0.50
     optimization
    0.49
     SaaS
    0.49
     Optimize
    0.49
     unidirectional
    0.48
     uptime
    0.48
     iterative
    0.48
    POSITIVE LOGITS
     blackmail
    0.96
     humiliated
    0.79
     incriminating
    0.78
     mariage
    0.76
     divorce
    0.75
     marriage
    0.74
     scandal
    0.74
     betray
    0.74
     confessed
    0.73
     betrayed
    0.73
    Act Density 0.018%

    No Known Activations