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

    Neuronpedia

    INDEX
    Explanations

    symbols and multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dollars
    0.52
    f
    0.51
     Dollars
    0.46
     introductions
    0.45
    导
    0.44
    er
    0.44
     modifications
    0.43
     dollars
    0.43
    ++
    0.43
     assignments
    0.43
    POSITIVE LOGITS
     सुनिश्चित
    0.48
     ব্র
    0.46
     रि
    0.45
     başar
    0.44
     മാലി
    0.43
     ס
    0.42
     ฮ
    0.42
     ஹ
    0.42
     ラ
    0.42
     gewährleisten
    0.42
    Act Density 0.000%

    No Known Activations