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

    Neuronpedia

    INDEX
    Explanations

    sage, contempt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    btnInventory
    0.49
    寘
    0.48
    ühlt
    0.48
    Bokeh
    0.46
     κάνει
    0.45
    一层
    0.44
    屽
    0.44
    诨
    0.44
     οικο
    0.43
     Patreon
    0.43
    POSITIVE LOGITS
     hospitable
    0.45
     diphtheria
    0.44
     millennium
    0.40
     hospitals
    0.40
     postwar
    0.39
     scientific
    0.39
     জাতীয়
    0.39
     curricula
    0.39
     ۱۹
    0.39
     প্রভৃতি
    0.38
    Act Density 0.005%

    No Known Activations