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

    Neuronpedia

    INDEX
    Explanations

    honor

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    นำ
    0.69
     শহরের
    0.68
     elektro
    0.68
     דבר
    0.67
     SAE
    0.64
    िच
    0.64
    咉
    0.63
    adress
    0.63
     मूल्यांकन
    0.61
     πο
    0.61
    POSITIVE LOGITS
     honour
    1.05
     honor
    1.04
     Honor
    1.01
    Honor
    0.98
     honored
    0.95
    honor
    0.94
     honoured
    0.91
     honoring
    0.90
     Honour
    0.90
     honours
    0.89
    Act Density 0.178%

    No Known Activations