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

    Neuronpedia

    INDEX
    Explanations

    to be or was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     travaillons
    0.43
     curve
    0.43
     recibieron
    0.41
     curves
    0.41
     '+'
    0.41
     получают
    0.40
     constraints
    0.40
     Ons
    0.40
     fetchData
    0.39
    addTask
    0.39
    POSITIVE LOGITS
     تكون
    0.70
     يكون
    0.66
    成为
    0.65
     geworden
    0.64
     siendo
    0.63
     become
    0.63
     becoming
    0.63
    Being
    0.62
     быть
    0.61
    成為
    0.61
    Act Density 0.021%

    No Known Activations