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

    Neuronpedia

    INDEX
    Explanations

    anomaly, fraud detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recalculated
    0.98
     분석
    0.97
    调整
    0.96
    分析
    0.94
     分析
    0.93
     reorgan
    0.92
     interviewing
    0.90
     inspecting
    0.90
    评估
    0.90
     EVAL
    0.88
    POSITIVE LOGITS
    การ
    0.99
     প্ৰ
    0.93
     इनकी
    0.86
     การ
    0.85
    প্র
    0.83
     प्र
    0.83
     इनका
    0.82
     નું
    0.79
    प्र
    0.77
    ONE
    0.76
    Act Density 1.580%

    No Known Activations