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

    Neuronpedia

    INDEX
    Explanations

    giving recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.71
     abstra
    0.67
     importante
    0.65
     geschrieben
    0.59
    </strong>
    0.59
    </sup>
    0.57
    IA
    0.57
     antiguo
    0.56
    意识到
    0.56
     ق
    0.55
    POSITIVE LOGITS
    recommended
    0.89
     recommend
    0.88
     recommended
    0.85
     recommending
    0.85
    recommend
    0.80
     Recommend
    0.79
     recommendation
    0.78
     recommand
    0.75
    オススメ
    0.75
     recomend
    0.74
    Act Density 0.107%

    No Known Activations