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

    Neuronpedia

    INDEX
    Explanations

    history artifacts repatriation debate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    중에
    0.49
     כבר
    0.47
     अगेन
    0.45
    መም
    0.45
     있음
    0.44
     unità
    0.43
     encaps
    0.43
    单元
    0.43
     melodrama
    0.42
     indispensables
    0.42
    POSITIVE LOGITS
    0.44
    AD
    0.44
    ä
    0.42
     repatri
    0.42
    arning
    0.42
     Vorteile
    0.41
     repatriation
    0.41
    ka
    0.41
    ad
    0.40
    海外
    0.40
    Act Density 0.013%

    No Known Activations