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

    Neuronpedia

    INDEX
    Explanations

    questions or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Khalid
    0.43
     данных
    0.43
     данные
    0.43
     निघ
    0.43
     देखते
    0.40
    আমিন
    0.40
     પ્રસ
    0.39
     известные
    0.38
     истины
    0.38
     판단
    0.38
    POSITIVE LOGITS
     optimizes
    0.40
     nozzle
    0.39
    ەس
    0.38
    ąz
    0.38
     steel
    0.37
     vada
    0.37
     horseshoe
    0.37
     dinam
    0.37
     dynamism
    0.37
     بغ
    0.37
    Act Density 0.000%

    No Known Activations