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

    Neuronpedia

    INDEX
    Explanations

    relationship issues and emotions

    np_acts-logits-general · gemini-2.5-flash-lite

    first-person narratives about romantic relationship conflict, especially shifts in affection, betrayal/infidelity, and communication breakdowns.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    The
    0.53
     zeich
    0.52
     podem
    0.51
     Б
    0.50
     Вер
    0.50
     The
    0.48
    quel
    0.48
     arba
    0.47
     ;-)
    0.47
     intrepid
    0.47
    POSITIVE LOGITS
     coworker
    0.67
     hurtful
    0.65
     আমাকে
    0.64
     abusive
    0.61
     boyfriend
    0.59
     నేను
    0.58
     mujhe
    0.57
     tbh
    0.57
     psychosis
    0.57
     psychiatrist
    0.57
    Act Density 0.043%

    No Known Activations