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

    Neuronpedia

    INDEX
    Explanations

    personal relationship descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cznej
    0.84
    czną
    0.80
    yny
    0.77
    torque
    0.75
    ckiej
    0.74
    最大
    0.73
    洼
    0.70
    Ahh
    0.70
    ாரம்
    0.66
    Max
    0.66
    POSITIVE LOGITS
     husband
    0.96
    itability
    0.89
     husbands
    0.88
     breasts
    0.86
     earrings
    0.81
     chồng
    0.79
    妆
    0.77
    龄
    0.76
     பிள்ள
    0.76
     boyfriend
    0.76
    Act Density 0.000%

    No Known Activations