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

    Neuronpedia

    INDEX
    Explanations

    finding oneself or others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あとは
    1.50
    鹉
    1.46
    ق
    1.45
    gada
    1.39
     світі
    1.37
    ӹ
    1.37
     misconceptions
    1.36
     squamous
    1.36
     wafer
    1.35
    )\|_{
    1.34
    POSITIVE LOGITS
     Nemo
    2.06
    NavController
    2.05
    withtag
    2.04
     kiếm
    1.94
     excuses
    1.89
    م
    1.87
     solace
    1.87
    ividual
    1.76
    herent
    1.67
    lägg
    1.65
    Act Density 0.088%

    No Known Activations