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

    Neuronpedia

    INDEX
    Explanations

    trustworthiness and reputation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    改变
    0.42
     计算
    0.40
     zmniejs
    0.40
     நகர
    0.40
     shimmering
    0.38
    LensFlare
    0.38
     tâche
    0.38
     为
    0.38
    初始化
    0.38
    urètre
    0.38
    POSITIVE LOGITS
     reputable
    0.80
     reputation
    0.79
     reputations
    0.68
     credentials
    0.63
     Reputation
    0.63
     trustworthiness
    0.62
     certifications
    0.62
     reput
    0.61
     trustworthy
    0.60
     fiabilité
    0.59
    Act Density 0.146%

    No Known Activations