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

    Neuronpedia

    INDEX
    Explanations

    in order to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.47
     उतरे
    0.46
    وای
    0.46
    eş
    0.46
    vo
    0.45
     "]";
    0.45
    speed
    0.45
    SPEED
    0.44
    Ş
    0.43
    EYER
    0.42
    POSITIVE LOGITS
    liness
    0.54
     érdekében
    0.42
     सुनिश्चित
    0.40
    astics
    0.39
     fulfill
    0.39
     обеспечить
    0.39
     обеспечения
    0.38
    滝
    0.37
     achieve
    0.37
    ToReference
    0.37
    Act Density 0.007%

    No Known Activations