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

    Neuronpedia

    INDEX
    Explanations

    file not found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undes
    0.38
     Algebraic
    0.37
     processed
    0.36
     unwarranted
    0.36
     সীমা
    0.36
     gender
    0.36
     outliers
    0.35
    odimensional
    0.35
     થ
    0.34
    良好
    0.34
    POSITIVE LOGITS
     missing
    0.87
    Missing
    0.86
    missing
    0.86
     Missing
    0.84
    找不到
    0.82
    缺失
    0.80
     отсут
    0.79
     absence
    0.77
    缺少
    0.76
     fehlt
    0.72
    Act Density 0.018%

    No Known Activations