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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     помогает
    0.93
     поможет
    0.92
     помогают
    0.87
    有助于
    0.85
     afectan
    0.82
     ayudará
    0.80
     najbolje
    0.80
     يؤ
    0.79
     accompanies
    0.79
    helps
    0.78
    POSITIVE LOGITS
     быть
    1.60
     become
    1.60
     becoming
    1.53
     להיות
    1.44
     Become
    1.44
    变得
    1.44
    become
    1.41
     being
    1.41
    Become
    1.39
     být
    1.36
    Act Density 0.995%

    No Known Activations