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

    Neuronpedia

    INDEX
    Explanations

    influx of people, needs updating, word to, NOT click, fuels addiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಉತ್ತಮ
    0.55
    кг
    0.51
     شرطونه
    0.50
     теркәлүсез
    0.50
    0.50
    カム
    0.50
     CustB
    0.49
    යින්
    0.49
     नाव
    0.48
     వారు
    0.48
    POSITIVE LOGITS
     a
    0.51
    ,
    0.47
    D
    0.46
    J
    0.45
    -
    0.45
    F
    0.45
    es
    0.44
     open
    0.44
    G
    0.43
     Field
    0.43
    Act Density 0.001%

    No Known Activations