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

    Neuronpedia

    INDEX
    Explanations

    std; in c++

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ik
    0.45
     посредством
    0.42
    um
    0.41
     xsi
    0.41
    ich
    0.41
    aky
    0.40
     getData
    0.40
    ship
    0.39
    ick
    0.39
    ilung
    0.39
    POSITIVE LOGITS
    晧
    0.47
     ಆಯ್
    0.46
     ಇದು
    0.43
     పాఠ
    0.42
    럏
    0.40
     아주
    0.40
    쪽에
    0.40
    ეგის
    0.40
    리가
    0.40
     trivially
    0.40
    Act Density 0.001%

    No Known Activations