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

    Neuronpedia

    INDEX
    Explanations

    link closing followed by https

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    执行
    0.82
    0.81
     à
    0.79
    击
    0.78
    烛
    0.77
    ക്കളുടെ
    0.77
    DUCT
    0.77
     single
    0.76
     sting
    0.76
     resist
    0.75
    POSITIVE LOGITS
     चर्चित
    0.81
     znale
    0.80
    姪
    0.79
     desto
    0.77
    గా
    0.76
    uradaki
    0.76
    齟
    0.75
    info
    0.75
    িগ্ন
    0.74
     geodesic
    0.73
    Act Density 0.454%

    No Known Activations