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

    Neuronpedia

    INDEX
    Explanations

    fiercely loyal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    缓解
    0.76
    娑
    0.74
     masaje
    0.74
    ផ
    0.74
     soup
    0.73
    เนิน
    0.72
    预览
    0.71
     facilitator
    0.70
     astrophys
    0.70
     nib
    0.70
    POSITIVE LOGITS
     loyalty
    4.08
     loyal
    3.80
     Loyalty
    3.59
    Loy
    3.32
     Loyal
    3.16
     allegiance
    2.89
    loy
    2.88
    忠
    2.84
     loy
    2.83
     faithful
    2.82
    Act Density 0.178%

    No Known Activations