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

    Neuronpedia

    INDEX
    Explanations

    final answer is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Experience
    0.80
    FW
    0.77
    →</
    0.76
     Refuge
    0.72
     Race
    0.71
    ณ์
    0.71
     Inspirational
    0.70
     পাচ
    0.70
    Five
    0.70
     Perseverance
    0.69
    POSITIVE LOGITS
    협
    0.78
     পরিষ
    0.70
     slags
    0.69
    ◟
    0.69
     असताना
    0.69
     '-'
    0.68
    性价比
    0.66
     nonetheless
    0.65
     trad
    0.65
    aker
    0.65
    Act Density 0.011%

    No Known Activations